SCHOOL OF ELECTRICAL AND ELECTRONICS

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

UNIT – I – eHEALTH-SECA4004

1
 SECA4004 eHealth L T P Total
C
r
marks
e
d
i
t
s
3 1 0 100
3
Pre requisite: NIL Co Requisite: NIL

Course Objectives
 To introduce the concepts of eHealth
 To have an in-depth knowledge on medical data analytics and wearable devices used
in eHealth systems
 To assess the advantages of eHealth
 To explore the usage of AI in eHealth
 To design and develop applications for eHealth

UNIT CONTENTS HOURS

I INTRODUCTION TO eHealth 9
Overview and introduction to eHealth and flow of health information-
International regulations in eHealth-Advantages, Challenges and future
of eHealth.
II MEDICAL DATA ANALYTICS AND WEARABLE DEVICES 9
Health care data and Electronic Health Records (EHR) systems
Medical data bases –Wearable devices-Data collection from wearable
devices- Clinical use of personal health data- Big data in the field of
Medicine.
III DIGITAL HEALTH 9
Introduction to health care digital transformation- Digital health: Tools
Strategies of digital health-Technologies in digital health Implementation
of Digital health- Advantages and challenges of Digita
health.
IV ARTIFICIAL INTELLIGENCE IN eHealth 9
History of AI in health care-Impacts and Aspects of AI in health care-
Current research in AI in eHealth-Regulations and Ethical concerns
in using AI in eHealth.
V APPLICATION DEVELOPMENT FOR eHEALTH 9
Introduction to Android, Creating Android Activities, Android Use
interface design, Access Wi-fi and Bluetooth with mobile applications
Web based App for eHealth applications.

Maximum Hours: 45

2
Course Outcomes
On Completion Of The Course, Student Should Be Able To
Co1 – Articulate Ehealth And Its Regulations
Co2 – Explore Medical Data Analytics And Records
Co3 – Appraise Digital Transformation in the field of Medicine
Co4 – Analyse Ai In Health Care Systems
Co5 – Design System Level Architecture For HealthInformation Systems
Co6 – Deploy Android Application On Devices.

TEXT / REFERENCE BOOKS

1. Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in Health
Care and Biomedicine, Springer-Verlag London 2014.
2. Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionalsand
Policymakers. 2016.
3. Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and information
technology professionals. Lulu Press. 2014 Seventh edition.
4. Gaddi Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic libraryholding in the
Health Science Library

3
UNIT-1 INTRODUCTION TO eHEALTH
Overview and introduction to eHealth and flow of health information- International
regulations in eHealth-Advantages, Challenges and future of eHealth.

1.1 OVERVIEW AND INTRODUCTION

e-HEALTH is defined as:

Application of the Internet and other related technologies in the healthcareindustry to improve the
Access,Efficiency ,Effectiveness,Quality of treatment and Business process utilized by
healthcare organizations, practitioners, patients and consumers with the help of next generation
networks (NGN) to Improve the health status of patients.

WHO defines e-Health as...

e-Health is the cost effective and secure use of information and communication
technologies in support of the health and health related fields including healthcare, health
surveillance and health education, knowledge and research.

NGN
NGN : Next Generation Networks

With recent trends and technology advancement in the development of converged broadband
next generation networks (NGNs) and advanced multimedia services,
the potential has increased in delivering of various e-Health services to end users “anywhere,
anytime”. as shown in figure 1.1

Figure 1.1 Next Generation Network

4
QoS : Quality of Service

The wide variety of e-Health services impose different Quality of Service (QoS)
requirements on underlying network as shown in figure 1.2

Figure 1.2. QoS

5
QoS Requirements for e-Health Service
e-Health Service Classification is shown in figure 1.3

e-Health Classification

Figure 1.3 ehealth classification

6
Tele-Consult or e-consult or Tele-Medicine

It involves real-time video conferencing and streaming of ECG signals between a

patient and a doctor. The service enables a patient or doctor to initiate an e-consult session
using an appropriate research prototype client service media application as shown in figure
1.4

Figure 1.4 Telemedicine

ehealth Related services

 Index of available programs and services.

 Calendar of events.

 Patient satisfaction surveys.

 Service provider directories.

 Patient e-mail services.

 Health news.

7
m-Health

 m-Healthincludes the use of mobile devices in collecting aggregate and patient level
health data.
 Providing healthcare information to practitioners, researchers, and the patients. It
ensures agreat support

Definition of E-Health
 E-health is an emerging field in the intersection of medical informatics, public health and
business, referring to health services and information delivered or enhanced through the
Internet and related technologies. In a broader sense, the term characterizes not only a
technical development, but also a state-of-mind, a way of thinking, an attitude, and a
commitment for networked, global thinking, to improve health care locally, regionally,
and worldwide by using information and communication technology.

 USF Health points out that e-health uses technology to improve outcomes, certainly, but
also suggests that the idea has an additional goal:

 E-Health empowers patients to take an active role in their treatment, allowing them to
gain a deeper understanding of their conditions and how to effectively manage them.

 When taken within the context of this definition, e-health could signal an interesting, and
potentially seismic shift in the traditional doctor-patient relationship. Using technology to
assist in healthcare delivery means that patients have new ways to manage their own
treatment. Instead of relying on the physician to provide care, a virtual visit, remote
monitoring device, or even a smartphone, can engage the patient in new and sometimes
more proactive ways to improve their health. USF Health suggests:

 When patients have e-health resources available at their fingertips, they’re better
equipped to ask their physicians more pointed questions to understand their conditions
and better manage their health. People are more likely to complete treatment plans
recommended by physicians when they can research outcomes to learn the benefits of
prescriptions, exercises and other health activities designed to improve their conditions.
Sharing the burden of their own care increases patient satisfaction, as people are able to
gain a deeper understanding of exactly what their physician is doing to help them.

8
The 10 E’s of E-Health
The implications of this idea are profound and tied to the idea of digital technologies as
disruptors to every industry they’ve impacted, including healthcare. An article in the Journal of
Medical Internet Research recommended a framework for the idea of electronics in medicine,
providing us with a set of 10 “e’s” within the idea of e-health. The author states that any e-
health application should include:

 Efficiency in healthcare with the goal of decreasing costs. Telehealth applications meet
this goal by reducing overhead costs in a practice, decreasing wait times for
appointments, and also cutting encounter times.
 Enhancing care quality by empowering patients to participate in their own treatment
while also increasing convenience but cutting travel time and costs to and from a
provider.
 Evidence-based medicine tied to rigorous scientific frameworks with benchmarked
quality controls.
 Empowerment of consumers by expanding their knowledge base and allowing access to
electronic health records over the Internet, providing more patient-centered care and
caring.
 Encouragement of patient participation in more proactive care. For example, e-health can
help diabetics monitor their blood glucose levels and diet each day with the goal of
patient awareness and empowerment.
 Education of patients and their physicians through the use of Internet research and online
video or written health education information.
 Enabling easier exchange of information online between healthcare providers and their
patients.
 Extending healthcare beyond traditional boundaries, both geographically by providing
access to care in rural areas and conceptually.
 Ethically addressing new issues tied to patient-physician interaction, privacy, informed
consent, and equity issues.
 Equitable, especially as it pertains to offering care in rural areas where specialty or
primary care treatment may be lacking. Equity in care could also be related to the idea of
e-health as intersection of business and healthcare. Or even, the ability of consumers to
research physician performance scores online.

The U.S. Department of Health and Human Services published a brochure on the reach of
consumer e-health tools. The title is apt; the whole point of our digital evolution is that it’s
eally a revolution. According to the brochure, e-health tools help consumers engage in their own
care in new ways:

Consumers with diverse perspectives, circumstances, capacities, and experiences are included in
the design of, and have meaningful access to, evidence-based e-health tools with strong privacy
and security protections.

When taken within this framework, the idea of e-health facilitates an entire shift in traditional
healthcare models.

Telemedicine is E-Health
The increasing costs healthcare and the struggle to improve patient outcomes remains driving
factors behind the development of e-health tools. Telemedicine offers new ways to treat patients
9
with models that use the “10 e’s.” These models can include:

 Remote home monitoring.

 Patient education.
 Advanced home health.
 Direct patient virtual visits.
 Specialist consultations.

The global market for e-health tools is rapidly expanding. Within this context, OrthoLive has
introduced a tool designed for the specialty orthopedic provider to bring healthcare to the
patient. Whether at home or at work, the OrthoLive app helps improve quality outcomes in
healthcare. To find out more, contact us.

1.2 HEALTH INFORMATION SYSTEM

Definition
Health information system is that that systemin which collection, utilization, analysis and
transmission of information is done for conducting health services, training and research.
Objectives

 To provide reliable, latest and useful health information toall levels of health
 officers and administrators.
 To amend health policies and working system on the basisof feedback, received
 from health information system.
 To provide information about periodically and time boundprogrammes and for mid term
evaluation.
 To contribute towards achievement of objectives of healthpolicies and programmes.
 To increase efficiency and quality in health management.
Characteristics
 Facility for data fee back must be present in health informationsystem.
 Latest technology should be used in health information system.

 Unnecessary figures or data should not be present in information system.

 For information management, organizational structure must be present.

Domains/fields of health information system

It includes demography, vital statistics, healthsystem input, output, health determinants, health
economics, health status, health infrastructure, resources and outcome, financial statistics,
environmental health statistics as shown in figure 1.5

10
 Figure 1.5 Information Process

Steps Involved inRHIS Restructuring

Step 1: Carrying out service and information systemassessments

Step 2: Developing new sets of essential healthindicators

Step 3: Defining data sources and developing datacollection instruments for each of
the indicators selected

Step 4: Developing a data transmission andprocessing system

Step 5: Ensuring use of the information generated

Step 6: Planning for RHIS resources

STEP 1: Assessment of theExisting System

 Rapid Assessment of the current use andperformance ofthe existing system.

 Find out how and how well the current system works, to describe the variouscomponents of
thesystem and the organizational environment

STEP 2: Develop Essential Indicators

 Select essential indicators for management functions at each level of thehealth system:

11
  Health status (and disease surveillance) indicators
 Health services (and national program)indicators

 Resource indicators (human, physical, financial)

What Data Elements Should beCollected?

 Can provide useful information (affecting themanagement decisions)

 Cannot be obtained elsewhere

 Are easy to collect

 Do not require much work or time

 Can be collected relatively accurately

 Data-Led
 Focuses on the need to collect data which is required, is ofinterest, or may be useful

 Is usually vague on what information output can beobtained from

data

Action - led

 Focuses on the need to collect data that reflect identifiedpriority health needs & are
required by pre-determined indicators
 Indicator driven – national & local

 Usually directly linked to specific objectives and targets

Action-led systems are the most practical way to go as shown in figure 1.6

Figure 1.6 EDS at each level

12
Step 3: Data Sources and DataCollection Tools

Defining data sources and developing data collection instruments for eachof the indicatorsselected.

Data collection

 start small - as data quality improves & systemsare streamlined - add slowly

 collect data – linked to objectives - that can beused to calculate indicators

Data Sources and Data CollectionTools(continued)

 Collect only data that is easily available - determine easiest site for recording of data - donot
duplicate points of data collection

 Use clear & standardised definitions

 Train & provide ongoing support to data collectorsimprove data qualityUse a minimum number
of tools - user friendly,familiar & acceptable

Step 4: Developinga Data Transmissionand Processing System

 Information flows (including referral systems):

 Horizontal data transmission

 Vertical data transmission

 Use appropriate communication technology:

 Paper-based

 Electronic: Telephones, diskettes

Data Processing and Analysis

 Paper-based systems:

 Error-prone

13
  Computerized systems:

 Off-the-shelve versus customized

 Decision support systems

 Use of appropriate technology

 Capacity-building

Step 5: Ensuring Use of theInformation Generated

How can we improve information use?

 Ownership and relevance of the information must be felt among all potential users
of the information,through active participation in the system design

 Data need to be of appropriate quality, aggregatedat the right level, and produced
in a timely manner
Ensuring Use of the InformationGenerated (continued)

 Performance-based management systems tend toincrease use of information for

decision making.

 Cultural differences between data people andaction people can be

decreased through consensus building, teamwork, and training.

 Data presentation and communication (feedback)should be customized forusers at all levels

Step 6: Planning for RHIS Resources

 Adequate staffing

 Adequate logistic system for printed supplies

 Computer hardware/software and maintenance

 Communications equipment
14
  HIS line-item in MOH recurrent budget

The Prism Framework

 The Prism, or three-point framework, is predicatedon the assumption that

improving capacity in RHIS(and subsequently performance) requires
 interventions that address

 the environmental

 behavioral determinants of performance, and

 the technical determinants

It broadens analysis of routine health informationsystems to include the behavior of the collectors
and users of data and the context in which theseprofessionals work as shown in figure 1.7

Figure 1.7 Prism work

RHISPerformance Diagnostic Tool

1. Data Quality Assessment at District orHigher Level

2. Use of Information Assessment at Districtor Higher Level

3. Data Quality Assessment at Facility Level

15
4. Use of Information Assessment at FacilityLevel

INTRODUCTION TO eHEALTH
 The World Health Organization (WHO) defines eHealth as “the costeffective and secure
use of information and communications technologies in support of health and health-
related fields, including health-care services, health surveillance, health literature, and
health education, knowledge and research.”

 Electronic health (eHealth) systems continue to hold great promise for improving global
access to healthcare services and health informatics, particularly in the developing world.

 Advancements in remotely administered medicine increasingly enable virtual multimedia

delivery of medical consultation, remote imaging services, specialized medical
diagnostics, and remote medical procedures
 . Standardized electronic medical records promise to facilitate the digital exchange of
patient data among a patient’s primary care physician and other health providers.

 Aggregated, anonymized health data mined from these digital records hold the potential
to improve the efficacy of health research.

16
 eHealth informatics and online health scholarship increasingly improve healthcare by
improving patients knowledge about medical conditions and treatments, provisioning
the latest medical scholarship and advancements to medical schools in poor and
underserved regions, and providing up-to-date healthcare information for policy
makers.

 Another long term trend in medicine is the use of genomic data (e.g. genetic markers), as

 Figure 1.8 Electronic Health Record

 part of personalized electronic health records, to assist with diagnosis and treatment
decisions.
 These same technological advancements in electronic healthcare are creating
heightenedpublic policy concerns about as shown in figure 1.8
 patient privacy,
 information security,
 Technological obstacles that hinder the promise of eHealth systems include the
 lack of global interoperability standards for eHealth and
 technical infrastructure barriers, particularly in the developing world.

17
  Many of these challenges can be addressed through advancements in technical standards
for eHealth.
 Standards create the necessary interoperability among healthcare systems; • minimize the
risks of new technology development; •prevent single vendor lock-in; reduce costs by
enabling market competition and eliminating the need for expensive and customized
solutions; ensure widespread adoption;
 address specific concerns about privacy, security, and patient identification.
 eHealth standardization landscape including initiatives by CEN, DICOM, HL7, and ISO,
as well as the ITU-• Activities within the ITU that will contribute to the global
deployment of efficient and secure eHealth systems.

1.3 EMERGING TRENDS IN eHealth SYTEMS

Describes four emerging trends in eHealth systems that use information and communication
technologies for the delivery of healthcare services and for the digital recordation, storage, and
sharing ofmedical information:

 Genomic Medicine

 Standardized Electronic Health Records

 Remote Healthcare and Diagnostics

 Aggregated Public Health Data.

Genomic Medicine

 Possibly the most significant trend in medicine will be the use of genomic data (e.g.
genetic markers) in assisting with disease prevention, diagnosis, and treatment decisions.
 Accordingly, one of the most forward-looking areas for standardization exists at the

18
  intersection of information technology and genomic medicine.
 A human genome contains all of a per- son’s genes andassociated DNA.
 The international project known as the Human Genome Project completed mapping the
entirehuman genome in 2003.
 The medical profession has just begun to use genetic information in direct clinical care.
 Clinical uses of genomic information include the ability to anticipate a patient’s response
to pharmaceutical therapies;
 the detection of diseases or tumors; and
 the identification of inherited conditions or a patient’s proclivity to devel- op a disease.

 For example,

 DNA tests for mutations of the BRCA1 andBRCA2 genes are indicators of hereditary
patterns of breast cancer.
 Medical experts believe society to be approaching “an era of ‘genomic medicine’ in
which new diagnostic and therapeutic approaches to common multifactorial conditions
are emerging.”
 As genomic medicine evolves, it will be exceptionally data intensive as well as
computationally demanding.
 The future of genomic medicine in clinical practice, also sometimes referred to as
personalized medicine, will rely upon the availability of sophisticated medical
information systems in provider facilities.
 On a more macro level, medical discoveries related to the identification of gene
mutations and variations will require “international collaborations of large-scale
sequencing centers generating terabytes of sequence data at speeds and costs that seemed
inconceivable 5 years ago.”
 At present, electronic health record systems are generally not equipped to accommodate
genomic data.
 As genetic testing, diagnosis, and treatment be- comes more commonplace, this
information will need to be held in electronic records and be able to be exchanged
among providers.
ITU-T TechnologyWatch

 There are many other intersections between genomic medicine and information and
communication technologies.

 One unique aspect of genetic testing is that patients have the option to bypass
healthcareproviders entirely and order genomic tests directly on the Internet.

 This is a rapidly advancing and controversial area of medicine.

 These tests are used for prenatal screening to identify genetic conditions in unborn
children; identification of inherited genetic conditions that predispose an individual to
certain conditions and illnesses; identification of whether an individual is a carrier of an
19
 altered gene;and diagnoses of specific diseases.

 Standardization efforts related to privacy, pseudonymization, and security have to extend

to direct consumption of genetic tests over the Internet in addition to health care provider
mediated testing and diagnosis.

Standardized Electronic Health Records

 Medical information systems have historically captured and stored clinical and
administrative patient data in proprietary formats only understood by a single system
and not interoperable with other providers’ systems.
 Emerging standards for Electronic Health Records (EHRs) are attempting to create
common digital formats and structures for integrating a variety of information about a
patient and allowing this information to be exchanged among medical information
systems developed by different manufacturers.
 As shown in the ac- companying figure 1.9, the types of information integrated within
EHRs include clinical observations, medical histories, treatments, allergies, diagnostic
images, legal permissions, patient information, and drugs administered.

Figure 1.9 Integrated EHR

 It also requires a universal identification number system to uniquely identify each patient.

 On an even more practical level is the question of where, physically, the personalized
electronic health records are stored, whether on a computer in a primary care provider’s
office or on a government or third party server.

 The decision about where to store the information will have repercussions to the
longevity, security, and quality of the stored electronic records.
 Personalized electronic healthcare records also raise concerns about data security and
individual privacy.
20
  Social questions include the extent of user control over the content of electronic
healthcare records as well as control over who has access to these records.
 One often cited concern is the risk of discrimination in em- ployment or insurance and the
extent to which health insurance companies or employers might gain access to these
records.
 From a security standpoint, systems have to meet stringent authentication standards for
identifying and verifying the individuals attempting to access their own records as well as
for providers accessing these records .e protection of data while digitally stored or while
transmitted over a telecommu-nication network is similarly a critical requirement.
Remote Healthcare and Diagnostics

 In the developing world and in isolated geographical areas with limited access to health
providers and advanced medical technologies, remote electronic health services over
telecommunications services are increasingly filling gaps in medical care.
 Historically called “telemedicine,” remote healthcare services use telecommunication
networks and information technology for many medical purposes including remote clinical
care, diagnostics, electronic patient monitoring and patient and provider access to medical
information.
 None of these remote medical services is possible without telecommunications networks and
standards that enable adequate interoperability, quality of service, and security

Remote Clinical Care

 Remote clinical care increasingly enables doctors located at a distance from patients to
provide electronic medical assessments, diagnoses, and treatments.
 It also allows doctors not in the same location to discuss patient diagnoses.
 If a patient is geographically distant from medical care but has access to a
telecommunications network and computer or cell phone, medical providers can administer
remote clinical care.
 This approach involves real- time and interactive communications between a doctor and a
patient, either on a phone (landline or mobile) or via video communications over a computer.
 This direct clinical care via a telecommunications network usually requires the simultaneous
online or electronic presence of both the patient and the medical provider/s.
 Other forms of remote diagnostics involve “store and forward” electronic health services that
acquire some aspect of medical information (such as an MRI, ultrasound, or other
radiological image) and then transmit this information to a medical practitioner for analysis
at a later time

Electronic Patient Monitoring

 Remote patient monitoring refers to the ability of medical providers to electronically observe
a patient remotely using medical monitoring devices and telecommunication networks.
 For example, a medical practitioner can monitor such characteristics as a patient’s heart
rhythms, blood pressure, pulse oximitry, pulmonary functionality, or blood glucose level.
 This type of remote health care monitoring can be used to cost effectively monitor patients
with chronic conditions, the elderly, and patients recovering from a specific condition.

21
Mobile Healthcare

According to ITU statistics, there were an estimated 4.6 billion mobile phone subscribers worldwide
at the end of 2009 and more than half of the population of the developing world had mobile phone
service.Particularly in the developing world, mobile phones are becoming a new medium for health
delivery, both through voice communications and via text messages and multimedia.This is the case
both in urban areas and in poorer and more rural areas with limited computing infrastructures other
than cellular phone networks.In some cases, government officials and NGOs use mobile phones to
gather public health-related data and to monitor general health conditions.Mobile phones also help
networks of health providers to stay current about general health issues, medical advancements,
pharmaceutical notifications, or to access information about a particular patient.Remote patient-to-
physician communication via a mobile device is an increasingly common part of health care as is
patient selfeducation and access to medical information via mobile devices.Further advances are
expected in medical monitoring technologies that can transmit diagnostic statistics to a provider via
a mobile phone network.

Challenges to emerging mHealth (mobile health) applications are numerous,including

how to ensure the accuracy of medical information obtained by patients via mobile devices, how to secure
patient-to-provider communications over mobile networks, and how to guarantee adequate service reliability
for remote monitoring functions.

Aggregated Public Health Data

 The global eHealth landscape is still fragmented in that hospitals, physicians’ offices,
pharmacies, and other healthcare providers have transitioned to digital record keeping
systems but do not necessarily have systems that interoperate with each other.
 The data portability and system interoperability expected to accompany electronic health
records and emerging eHealth systems will not only improve health delivery and create
cost efficiencies, but will present unprecedented opportunities for the mining of
aggregated public health data.
 The term “aggregated health data” refers to a large body of data obtained by combining
some characteristics of standardized digital health records in a way that removes
information that would identify any individual patient.
 This data is not used for direct care of individuals or for insurance and billing purpos- es
but for some secondary use related to research, public health assessments, accreditation,
patient education, or some commercial purpose.
 These functions are often referred to as “secondary uses of health data.”

Aggregated Public Health Data

 Even though the vast majority of electronic health information is currently not
aggregated, there is already a multi-million dollar business based on collections of health
data, flowing through two primary aggregation points.
 Smaller aggregators include provider entities such as hospital networks and pharmacies.
Many of these data collection efforts take place through billing systems and other
administrative recordation.
 Larger aggregators include hospital associations and corporations who buy anonymized
health data from smaller aggregators, further aggregate this information and then sell it
for profit.

22
Aggregated Public Health Data
 Standards will play a critical role in both achieving the public health benefits of aggregated
patient data and providing solutions to requirements for security, privacy, quality assurance,
and interoperability.
 As long as electronic health records are fragmented technically without adequate
standardization among providers and vendors, meaningful public aggregation will not be
possible.
 This standardization requirement spans all areas of information protocols ranging from
standardized codes for specific procedures, data formatting standards, compression
standards, and network level standards.
 HL7 partners with other institutions, such as the International Organization for
Standardization (ISO) in issuing international eHealth standards, (ISO/HL7 21731:2006
Health Informatics-HL7 version 3-Reference Information Model).

1.4 LANDSCAPE OF EHEALTH STANDARDIZATION

Many standardization organizations, including ITU, work on various areasof eHealth.
 The eHealth Standardization Coordination Group (eHSCG), supported by ITU-T Study
Group 16, maintains a list of standards in both technical and non-technical areas of eHealth
on the World Health Organization web site. This section briefly describes a variety of
eHealth standardization initiatives including:
 DICOM

 CEN/TC 251

 HL7

 ISO/TC 215

 ISO/IEEE 11073.
DICOM
 Digital Imaging and Communications in Medicine (DICOM) is a standard forexchanging
medical images.

 More specifically, it is a file format and transmission standard for exchanging medical
images and associated information between medical imaging equipment made by different
manufacturers.
 The DICOM standards are widely adopted in equipment and information systems used in
hospitals, imaging centers, and in providers’ offices to produce, display, store, or exchange
medical images.
 The standard provides a number of specifications including:
 Network protocols
 Syntax and semantics of commands and associated information
 Media storage services, file formats, medical directory structure

23
  There are twenty DICOM working groups, made up of technical and medical professionals,
which maintain the various DICOM standards.
 The National Electrical Manufacturers Association (NEMA) oversees and holds a copyright
to the DICOM standards, originally developed by a joint committee formed by NEMA and
the American College of Radiology.
CEN/TC 251

 The Comité Européen de Normalisation or European Committee for Standardization (CEN)

is a standards development organization made up of 31 national members developing pan-
European standards.
 CEN has a Health Informatics Technical Committee (TC 251) which coordinates the
development of standards for eHealth.
 According to its business plan and recent activities, the focus of CEN/TC 251 is primarily on
technologies at the content level rather than dealing with communication technologies.
 CEN/TC 251 is further broken down into working groups such as Working Group IV, which
focuses on the interoperability of data among devices and information systems.
HL7

 Health Level Seven (HL7) is a standards development organization which issues

international application layer healthcare standards for the electronic exchange and management of health
information such as clinical data and administrative information.
 HL7 refers to the standards organization itself but is also com- monly used to refer to specific
standards the institution develops. HL7 dates back to the mid1980s, when it was formed to
develop a standard for hospital information systems.
 Like other standards organizations, HL7 is organized into Work Groups chaired by two or more
co-chairs and responsible for defining some area of HL7 standards.
 HL7 has dozens of Work Groups, including groups addressing electronic health records,
infrastructure and messaging, and imaging integration.
 To provide one example of an HL7 specification, the HL7 Clinical Document Architecture
(CDA) serves as an XML-based markup standard defining the structure, encoding parameters,
and semantics of electronic clinical documents.
 There is also a Work Group on clinical genomics, formed to develop common standards for
genomic information/data across many organizations ranging from research institutions, medical
practitioners, and regulatory bodies as appropriate under existing law.
 Part of the Work Group’s charter is to review what data needs to be exchanged and to identify
and review existing standards for genomic data. HL7 partners with other institutions, such as the
International Organization for Standardization (ISO) in issuing international eHealth standards,
(ISO/HL7 21731:2006 Health InformaticsHL7 version 3-Reference In- formation Model).

ISO/TC 215

 ISO's Technical Committee 215 also addresses health informatics.ISO/TC 215 focuses
primarily on elec- tronic health records.
 Various Working Groups (WGs) within TC 215 address topics such as data structure,
messaging and communication, security, pharmacy and medication, devices, and business
requirements for electronic health records.

24
  For example, ISO/TS 25237:2008 addresses pseudonymization principles and re-
quirements for privacy protection of electronic health records.
 Many of ISO’s standards are collaborations or endorsements of standards developed by other
standards organizations such as HL7 or IEEE.
 For example, ISO/HL7 27931:2009, “Data Exchange Standards Health Level Seven Version
2.5” establishes an application protocol for electronic data exchange in healthcare
environments.

ISO/TC 215
 At present, ISO Technical Committee 215, WG 8 (Business Requirements for Electronic
Health Records) is also developing a technical report (TR) in partnership with the WHO to
make international eHealth standards more accessible to developing countries.
 The objective of this report will be to guide developing countries in adopting universal
standards for health informatics systems. The first part of the report will be descriptive and
provide an overview of existing international standards for eHealth.
 The second part of the report will offer a “roadmap for identifying business requirements to
define an eHealth enterprise architecture.”

ISO/IEEE 11073

 ISO/IEEE 11073 Medical/Health Device Communication Standards are a set of joint ISO,
IEEE, and CEN standards for medical device interoperability.
 In this context, medical devices include primarily personnel, or end user, health devices such as
blood glucose monitors, blood pressure monitors, thermometers, pulse oximeters, etc., that
patients use in their own homes or other end points to monitor existing medical condi- tions.
 The ISO/IEEE 11073 (formerly called IEEE 1073) standards define messaging structures but
not the transport layer upon which messages are transmitted.

ITU-T MULTIMEDIA FRAMEWORK FOR EHEALTH APPLICATIONS

 ITU Recommendations underlie much of the telecommunications infrastructure

necessary for supporting the virtual multimedia delivery of medical care, remote diagnostic
services, and electronic medical records.
 ITU Study Groups address these infrastructural issues as well as generally addressing many
emerging eHealth related requirements for
 security (Study Group 17),
 performance and quality of service (Study Group 12),
 multimedia coding and systems (Study Group 16), mobile telecommunications networks
(Study Group 13), and a host of other areas.
 For example, the H.300-series, H.260-series, V.18, T.80-series, and T.800-series all have
direct bearing upon eHealth systems.
 More specifically though, eHealth standardization studies in the Standardization Sector of
theITU-T are addressed “Multimedia Framework for e-health Applications.”
 This high-level Question, which coordinates the technical standardization of multimedia
systems to support eHealth applications, is allocated under ITU-T Study Group 16, the Lead
Study Group on ubiquitous applications (e.g. eHealth and eBusiness).
 This work originally emanated from a workshop held in 2003 involving the key
25
 standardization players at the time, together with the creation of the eHealth Standardization
Coordination Group (eHSCG).
 The overarching objective of the eHSCG is to “promote stronger coordination amongst the
key players in the e-Health Standardization arena.”
 The eHSCG, through informal coordination on a voluntary basis, hopes to facilitate an
exchange of information among standardization organizations to avoid duplication of effort.
 It seeks to consider the requirements of developing countries and to serve as a technical
rather than regulatory coordination group, albeit taking into consideration social, economic,
and regulatory factors.
 The Telecommunication Standardization Bureau of the ITU, through ITU-T Study Group 16,
provides direct support for the activities of the eHSCG, including web site and membership
management and the provisioning of necessary tools for the organization to work by
correspondence.
 Some of the study items for Question 28/16 include the development of an overall
framework for
 eHealth applications, and telemedicine in particular;
 the development of a roadmap for eHealth standards;

 a generic architecture for eHealth applications,and specific system characteristics for eHealth
applications such as video and still picture coding, audio coding, security, and directory
architecture.Some of the study items for Question 28/16 include the development of an overall
framework for eHealth applications, and telemedicine in particular; the development of a roadmap for
eHealth standards; a generic architecture for eHealth applications, and specific system characteristics
for eHealth applications such as video and still picture coding, audio coding, security, and directory
architecture.
 The tasks of Q28/16 include the following:

 Inventory of existing eHealth and telemedicine standards

 Roadmap for eHealth/telemedicine standards compiling and analyzing

standardization requirements from eHealth stakeholders and identifying
 standardization items with priorities

 Involvement in the eHealth Standardization Coordination Group

 Contributions to extensions and improvements of existing Recommendations on

multimedia systems (H.323, H.264, V.18, etc.)

 Development of new Recommendations if necessary.

 Q28/16 focuses on the critical need for global interoperability among fragmented eHealth
systems based on different standards and seeks to provide the necessary coordination among
major global players (e.g. medical institutions, governments, inter-governmental
organizations, non-profit groups, private industry).
 Q28/16 also produced a Roadmap for Telemedicine indicating major technologies that
applicable to tele-medicine and e-health and could benefit from standardization activities.

 The ITU-T’s eHealth Question 28/16, via Study Group 16, works with relevant consortia and
standardization bodies such as HL7, DICOM, ISO, ETSI, IETF, IEEE, IEC, CEN and other
26
 bodies, as well as the eHealth
 Standardization Coordination Group.

1.5 DIGITAL HEALTH SERVICES

Another of the great advantages of new technologies in the healthcare sector is how versatilethey are.
Here are some of the most widespread solutions they offer:
Telehealth. Providing care at a distance means people in remote areas with limited access to
healthcare can get the medical attention they need. It also saves time, money and travel for both
doctors and patients.
Apps. Having mobile apps dedicated to health turns our smartphones into personal trainers, sleep
monitors, diagnostic, devices and more, with apps for both healthcare professionals and patients.
Serious Games. These special video games are used as a learning resource for healthcare
professionals and students to enhance their training. They can also be used by people wishing to
learn more about specific pathologies.
Wearable technology. The well-known term wearables, includes smart clothing and accessories
such as wristbands, glasses and watches to monitor and collect information on our health and
physical condition.
Augmented reality. AR can help health professionals to visualise organs in 3D, for example, or
check a patient's record in real time. It can even be used in surgical procedures with special AR
headsets. eHealth record. Having a digital health record means information can be stored in one
place but be available anywhere, so patients can share it safely and healthcare staff can access it at
any time.

1.6 ADVANTAGES AND BENEFITS OF EHEALTH

Thanks to services like these, digital health enables us to apply new methods, means, tools and
channels that lead to a series of benefits:
 Improved patient monitoring
Communication is easier with this new digital channel, helping to bridge the gap between
doctors and patients. Technology also means the patient's condition can be monitored and
their progress can be recorded in real time.
 More informed patients
As patients, we can make better health decisions when we understand them and have the
power to manage their own health. ICTs also provide us with access to guide books and best
practice, something very useful, for instance, during the pandemic if they come from reliable
sources.
 Encouraging healthier habits

New technologies are changing the way we look after ourselves with apps and devices that
keep track of what we eat, how much exercise we do, how long or soundly we sleep and how
fast our heart rate is.
 Easier decision-making for healthcare staff

eHealth is also transforming the way professionals deal with disease. ICTs can help, for
instance, to identify optimal treatments more easily or detect illnesses at an early stage.
 More accessible and equal healthcare
Access to healthcare is no longer limited by time and space, which means avoiding
unnecessary travel. Moreover, technology brings healthcare to more people, especially
patients at risk of exclusion, which means more equal opportunities for everyone.
27
  More efficient hospitals and health clinics

Connected facilities mean a streamlined health system, minimise the chance of human error
and cutting costs. In addition, techniques such as big data, processes are being automated.

1.7 NEW TECHNOLOGIES IN eHEALTH

Digitising health involves using new technology. Here is some of them and their specific uses:

Internet of Things (IoT)

The Internet of Things helps to customise healthcare, save costs, reduce the likelihood of incorrect
diagnosis and shorten waiting times. The connection between the physical and digital world will be
crucial in equipment such as inhalers and audiometers.
Big data

Using big data to perform macro data analysis allows for tailored treatments and helps to detect the
risk factors and potential side effects of drugs. The insight gained from it has proven critical in
understanding and containing the spread of COVID-19.

Artificial Intelligence
Artificial intelligence can help healthcare professionals to make wiser decisions and deliver better
treatments. During the coronavirus crisis, AI was used to identify the sequence of antibodies and its
compatibility with future treatments.

Blockchain
Blockchain affords safe access to a patient's health record, which makes a more efficient
administration. It also allows pharmaceutical labs to keep a more precise record in the drug
production process. •3D and 4D printing
The use of 4D printing in ultrasound scans, for example, gives us more precise insight into the
structural and functional development of the nervous system of the foetus. Furthermore, the
shortage of safety equipment during the coronavirus crisis led to the production of medical items
using 3D printers.
Chatbots

Chatbots provide a tool to enable faster and more direct doctor-patient communication. The World
Health Organisation set up one of these channels during the COVID-19 pandemic.

Virtual reality
Some of the most significant contributions that VR technology can make include assisting with
patient rehabilitation and treating psychological disorders.

28
1.8 IMPORTANCE OF E-HEALTH

E-Health technology plays a significant role in providing healthcare services.

Some of the benefits are as follows:
 It helps in paperless record management as patients' medical record is stored in a centralized
database system. This avoids excessive use of papers
 It gives fast access to patients' medical record such as history of the patient, pathology and
diagnostic reports, prescription, and billing data. Any information related to patient can be made
available with few clicks
 It initiates easy collaboration between multiple departments in the hospitals as the same data
can be viewed by various physicians and surgeons
 It enhances efficiency of hospital and healthcare work as e-health technology is automated
and helps in fetching records which saves time and efforts of the staff
 E-Health technology provides accurate information so less chances of error in the entire
process of medical record maintenance
 It allows to book appointments for medical checkup. It also allows prior booking of
equipment which eliminates the chances of double booking
 It provides variable pricing list based on insurance policies, which makes billing process
easy and less time-consuming
 It generates graphical reports from the patients' data and provides secure storage of medical
records. It is user-friendly application with mobiles which is easy to navigate patient
information.
 Healthcare software is categorized on the basis of e-health information type.

TEXT / REFERENCE BOOKS

1.Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in Health Care and
Biomedicine, Springer-Verlag London 2014.
2.Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionals and
Policymakers. 2016.
3.Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and informationtechnology
professionals. Lulu Press. 2014 Seventh edition.
4.Gaddi A, Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic library holding in the Health
Science Library

29
 SCHOOL OF ELECTRICAL AND ELECTRONICS
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

UNIT – II – eHEALTH– SECA4004

30
UNIT-II MEDICAL DATA ANALYTICS AND WEARABLE DEVICES
Health care data and Electronic Health Records (EHR) systems- Medical data bases – Wearable
devices-Data collection from wearable devices- Clinical use of personal health data- Big data in
the field of Medicine.

2.1 INTRODUCTION TO BIG DATA

Large and complex data sets which are difficult to process usingtraditional database
technology.

Volume
Veracity

Velocity Variety
BIG
DATA

Big data is not just about size.

• Finds insights from complex, noisy,heterogeneous,
longitudinal, and voluminous data.
• It aims to answer questions thatwere previously

31
HEALTHCARE ANALYTICS IN THE ELECTRONIC ERA

 Old way: Data are expensive and small

– Input data are from clinical trials, which is

smalland costly

– Modeling effort is small since the data is

limited

Figure 2.1 HER era in old way

 EHR era: Data are cheap and large as shown in figure 2.1

 Broader patient population

 Noisy data

 Heterogeneous data

 Diverse scale

 Longitudinal records

EXAMPLES FOR BIG DATA ANALYTICS IN HEALTHCARE

Government Initiatives

 Medicare Penalties: Medicare penalizes hospitals that have high rates ofreadmissions
among patients with Heart failure, Heart attack, Pneumonia.

 BRAIN Initiative: Find new ways to treat, cure, and even prevent brain disorders, such
as Alzheimer’s disease, epilepsy, and traumatic brain injury. A new bold $100 million
research initiative designed to revolutionizeour understanding of the humanbrain.
Industry Initiatives

32
  Heritage Health Prize: Develop algorithms to predict the number of daysa patient
will spend in a hospital in the next year. http://www.heritagehealthprize.com
 GE Head Health Challenge: Methods for Diagnosis and Prognosis of Mild
Traumatic Brain Injuries. Develop Algorithms and Analytical Tools, and Biomarkers
and othertechnologies. A total of $60M in awards as shown in figure 2.2

DATA COLLECTION AND ANALYTICS

Figure 2.2 Data Collection and Analytics

Effectively integrating and efficiently analyzing various forms of healthcare data over a
period of time can answer many of the impending healthcare problems.

33
DIFFERENT KINDS OF OUTCOMES

Economic Cost
Continuous Outcomes

Presence ofa
disease Bi

nary Outcomes

What
Diagnostic
disease
Cat egorical Outcomes
How serious
Or

dinal Outcomes

ival Outcomes
Surv
Survival analysis
…

34
  Binary Outcomes
Death: yes/no
Adverse event: yes/no

Continuous Outcomes

 Days of Hospital stay

Visual analogue score

 Ordinal Outcomes
Quality of life scale
Grade of tumour progression

 Count data (Number of heart attacks)

Survival Outcomes
Cancer survival
Clinical Trials
Big data has changed the way we manage, analyze, and leverage data across industries. One of
the most notable areas where data analytics is making big changes is healthcare

2.2 BIG DATA IN HEALTHCARE

Big data in healthcare is a term used to describe massive volumes of information created by the
adoption of digital technologies that collect patients' records and help in managing hospital
performance, otherwise too large and complex for traditional technologies.

The application of big data analytics in healthcare has a lot of positive and also life-saving
outcomes. In essence, big-style data refers to the vast quantities of information created by the
digitization of everything, that gets consolidated and analyzed by specific technologies. Applied
to healthcare, it will use specific health data of a population (or of a particular

35
individual) and potentially help to prevent epidemics, cure disease, cut down costs, etc.

Now that we live longer, treatment models have changed and many of these changes are namely
driven by data. Doctors want to understand as much as they can about a patient and as early in
their life as possible, to pick up warning signs of serious illness as they arise – treating any
disease at an early stage is far more simple and less expensive. By utilizing key performance
indicators in healthcare and healthcare data analytics, prevention is better than cure, and
managing to draw a comprehensive picture of a patient will let insurance provide a tailored
package. This is the industry’s attempt to tackle the siloes problems a patient’s data has:
everywhere are collected bits and bites of it and archived in hospitals, clinics, surgeries, etc.,
with the impossibility to communicate properly.

Indeed, for years gathering huge amounts of data for medical use has been costly and time-
consuming. With today’s always-improving technologies, it becomes easier not only to collect
such data but also to create comprehensive healthcare reports and convert them into relevant
critical insights, that can then be used to provide better care. This is the purpose of healthcare
data analytics: using data-driven findings to predict and solve a problem before it is too late, but
also assess methods and treatments faster, keep better track of inventory, involve patients more
in their own health, and empower them with the tools to do so.

2.3 BIG DATA APPLICATIONS IN HEALTHCARE

Figure 2.3 Big data in Healthcare

Now that you understand the importance of health big data, let’s explore 18 real-world
applications that demonstrate how an analytical approach can improve processes, enhance
patient care, and, ultimately, save lives as shown in figure 2.3

1) Patients Predictions For Improved Staffing

For our first example of big data in healthcare, we will look at one classic problem that any shift
manager faces: how many people do I put on staff at any given time period? If you put on too
many workers, you run the risk of having unnecessary labor costs add up. Too few workers, you
can have poor customer service outcomes – which can be fatal for patients in that industry.

36
 Figure 2.4.Example of Big data
Big data is helping to solve this problem, at least at a few hospitals in Paris. A white paper by
Intel details how four hospitals that are part of the Assistance Publique-Hôpitaux de Paris have
been using data from a variety of sources to come up with daily and hourly predictions as
shown in figure 2.4 how many patients are expected to be at each hospital.

One of the key data sets is 10 years’ worth of hospital admissions records, which data scientists
crunched using “time series analysis” techniques. These analyses allowed the researchers to see
relevant patterns in admission rates. Then, they could use machine learning to find the most
accurate algorithms that predicted future admissions trends.

Summing up the product of all this work, the data science team developed a web-based user
interface that forecasts patient loads and helps in planning resource allocation by utilizing
online data visualization that reaches the goal of improving the overall patients' care.

2) Electronic Health Records (EHRs)

It’s the most widespread application of big data in medicine. Every patient has his own digital
record which includes demographics, medical history, allergies, laboratory test results, etc.
Records are shared via secure information systems and are available for providers from both the
public and private sectors. Every record is comprised of one modifiable file, which means that
doctors can implement changes over time with no paperwork and no danger of data replication.

37
EHRs can also trigger warnings and reminders when a patient should get a new lab test or track
prescriptions to see if a patient has been following doctors’ orders.

Although EHR is a great idea, many countries still struggle to fully implement them. U.S. has
made a major leap with 94% of hospitals adopting EHRs according to this HITECH research, but
the EU still lags behind. However, an ambitious directive drafted by the European Commission
is supposed to change it.

Kaiser Permanente is leading the way in the U.S. and could provide a model for the EU to follow.
They’ve fully implemented a system called HealthConnect that shares data across all of their
facilities and makes it easier to use EHRs. A McKinsey report on big data healthcare states that
“The integrated system has improved outcomes in cardiovascular disease and achieved an
estimated $1 billion in savings from reduced office visits and lab tests.”

3) Real-Time Alerting
Other examples of data analytics in healthcare share one crucial functionality – real-time alerting.
In hospitals, Clinical Decision Support (CDS) software analyzes medical data on the spot,
providing health practitioners with advice as they make prescriptive decisions.

However, doctors want patients to stay away from hospitals to avoid costly in-house treatments.
Analytics, already trending as one of the business intelligence buzzwords in 2019, has the
potential to become part of a new strategy. Wearables will collect patients’ health data
continuously and send this data to the cloud.

Additionally, this information will be accessed to the database on the state of health of the
general public, which will allow doctors to compare this data in a socio-economic context and
modify the delivery strategies accordingly. Institutions and care managers will use sophisticated
tools to monitor this massive data stream and react every time the results will be disturbing.

For example, if a patient’s blood pressure increases alarmingly, the system will send an alert in
real-time to the doctor who will then take action to reach the patient and administer measures to
lower the pressure.

Another example is that of Asthmapolis, which has started to use inhalers with GPS-enabled
trackers in order to identify asthma trends both on an individual level and looking at larger
populations. This data is being used in conjunction with data from the CDC in order to develop
better treatment plans for asthmatics.

4) Enhancing Patient Engagement

Many consumers – and hence, potential patients – already have an interest in smart devices that
record every step they take, their heart rates, sleeping habits, etc., on a permanent basis. All this
vital information can be coupled with other trackable data to identify potential health risks
lurking. Chronic insomnia and an elevated heart rate can signal a risk for future heart disease for
instance. Patients are directly involved in the monitoring of their own health, and incentives
from health insurance can push them to lead a healthy lifestyle (e.g.: giving money back to
people using smartwatches).

Another way to do so comes with new wearables under development, tracking specific health

38
trends, and relaying them to the cloud where physicians can monitor them. Patients suffering
from asthma or blood pressure could benefit from it, and become a bit more independent and
reduce unnecessary visits to the doctor.

5) Prevent Opioid Abuse In The US

Our fourth example of big data healthcare is tackling a serious problem in the US. Here’s a
sobering fact: as of this year, overdoses from misused opioids have caused more accidental
deaths in the U.S. than road accidents, which were previously the most common cause of
accidental death.

Analytics expert Bernard Marr writes about the problem in a Forbes article. The situation has
gotten so dire that Canada has declared opioid abuse to be a “national health crisis,” and
President Obama earmarked $1.1 billion dollars for developing solutions to the issue while he
was in office.

Once again, an application of big data analytics in healthcare might be the answer everyone is
looking for: data scientists at Blue Cross Blue Shield have started working with analytics experts
at Fuzzy Logix to tackle the problem. Using years of insurance and pharmacy data, Fuzzy Logix
analysts have been able to identify 742 risk factors that predict with a high degree of accuracy
whether someone is at risk for abusing opioids.

Figure 2.5 Drug Issue

39
To be fair, reaching out to people identified as “high risk” and preventing them from developing
a drug issue as shown in figure 2.5 is a delicate undertaking. However, this project still offers a
lot of hope towards mitigating an issue which is destroying the lives of many people and costing
the system a lot of money.

6) Using Health Data For Informed Strategic Planning

The use of big data in healthcare allows for strategic planning thanks to better insights into
people’s motivations. Care managers can analyze check-up results among people in different
demographic groups and identify what factors discourage people from taking up treatment.

The University of Florida made use of Google Maps and free public health data to prepare heat
maps targeted at multiple issues, such as population growth and chronic diseases. Subsequently,
academics compared this data with the availability of medical services in most heated areas. The
insights gleaned from this allowed them to review their delivery strategy and add more care units
to the most problematic areas.

7) Big Data Might Just Cure Cancer

Another interesting example of the use of big data in healthcare is the Cancer Moonshot program.
Before the end of his second term, President Obama came up with this program that had the goal
of accomplishing 10 years’ worth of progress towards curing cancer in half that time.

Medical researchers can use large amounts of data on treatment plans and recovery rates of
cancer patients in order to find trends and treatments that have the highest rates of success in the
real world. For example, researchers can examine tumor samples in biobanks that are linked up
with patient treatment records. Using this data, researchers can see things like how certain
mutations and cancer proteins interact with different treatments and find trends that will lead to
better patient outcomes.

This data can also lead to unexpected benefits, such as finding that Desipramine, which is an
antidepressant, has the ability to help cure certain types of lung cancer.

However, in order to make these kinds of insights more available, patient databases from
different institutions such as hospitals, universities, and nonprofits need to be linked up. Then,
for example, researchers could access patient biopsy reports from other institutions. One of the
potential big data use cases in healthcare would be genetically sequencing cancer tissue samples
from clinical trial patients and making these data available to the wider cancer database.

But, there are a lot of obstacles in the way, including:

 Incompatible data systems. This is perhaps the biggest technical challenge, as making
these data sets able to interface with each other is quite a feat.
 Patient confidentiality issues. There are differing laws state by state which govern what
patient information can be released with or without consent, and all of these would have
to benavigated.

40
  Simply put, institutions that have put a lot of time and money into developing their own
cancer dataset may not be eager to share with others, even though it could lead to a cure
much more quickly.

However, as an article by Fast Company states, there are precedents to navigating these types of
problems and roadblocks while accelerating progress towards curing cancer using the strength of
data analytics.

8) Predictive Analytics In Healthcare

We have already recognized predictive analytics as one of the biggest business intelligence trends
two years in a row, but the potential applications reach far beyond business and much further in
the future. Optum Labs, a US research collaborative, has collected EHRs of over 30 million
patients to create a database for predictive analytics tools that will improve the delivery of care.

The goal of healthcare online business intelligence is to help doctors make data-driven decisions
within seconds and improve patients’ treatment. This is particularly useful in the case of patients
with complex medical histories, suffering from multiple conditions. New BI solutions and tools
would also be able to predict, for example, who is at risk of diabetes and thereby be advised to
make use of additional screenings or weight management.

9) Reduce Fraud And Enhance Security

Some studies have shown that 93% of healthcare organizations have experienced a data breach.
The reason is simple: personal data is extremely valuable and profitable on the black markets.
And any breach would have dramatic consequences. With that in mind, many organizations
started to use analytics to help prevent security threats by identifying changes in network traffic,
or any other behavior that reflects a cyber-attack. Of course, big data has inherent security issues
and many think that using it will make organizations more vulnerable than they already are. But
advances in security such as encryption technology, firewalls, anti- virus software, etc, answer
that need for more security, and the benefits brought largely overtake the risks.

Likewise, it can help prevent fraud and inaccurate claims in a systemic, repeatable way.
Analytics help to streamline the processing of insurance claims, enabling patients to get better
returns on their claims and caregivers are paid faster. For instance, the Centers for Medicare and
Medicaid Services said they saved over $210.7 million in fraud in just a year.

10) Telemedicine
Telemedicine has been present on the market for over 40 years, but only today, with the arrival of
online video conferences, smartphones, wireless devices, and wearables, has it been able to come
into full bloom. The term refers to the delivery of remote clinical services using technology.

It is used for primary consultations and initial diagnosis, remote patient monitoring, and medical
education for health professionals. Some more specific uses include telesurgery – doctors can
perform operations with the use of robots and high-speed real-time data delivery without
physically being in the same location with a patient.

Clinicians use telemedicine to provide personalized treatment plans and prevent

41
hospitalization or re-admission. Such use of healthcare data analytics can be linked to the use of
predictive analytics as seen previously. It allows clinicians to predict acute medical events in
advance and prevent deterioration of patient’s conditions.

By keeping patients away from hospitals, telemedicine helps to reduce costs and improve the
quality of service. Patients can avoid waiting in lines and doctors don’t waste time on
unnecessary consultations and paperwork. Telemedicine also improves the availability of care
as patients’ state can be monitored and consulted anywhere and anytime.

11) Integrating Big-Style Data With Medical Imaging

Medical imaging is vital and each year in the US about 600 million imaging procedures are
performed. Analyzing and storing manually these images is expensive both in terms of time and
money, as radiologists need to examine each image individually, while hospitals need to store
them for several years.

Medical imaging provider Carestream explains how big data analytics for healthcare could
change the way images are read: algorithms developed analyzing hundreds of thousands of
images could identify specific patterns in the pixels and convert it into a number to help the
physician with the diagnosis. They even go further, saying that it could be possible that
radiologists will no longer need to look at the images, but instead analyze the outcomes of the
algorithms that will inevitably study and remember more images than they could in a lifetime.
This would undoubtedly impact the role of radiologists, their education, and the required skillset.

12) A Way To Prevent Unnecessary ER Visits

Saving time, money, and energy using big data analytics for healthcare is necessary. What if we
told you that over the course of 3 years, one woman visited the ER more than 900 times? That
situation is a reality in Oakland, California, where a woman who suffers from mental illness and
substance abuse went to a variety of local hospitals on an almost daily basis.

This woman’s issues were exacerbated by the lack of shared medical records between local
emergency rooms, increasing the cost to taxpayers and hospitals, and making it harder for this
woman to get good care. As Tracy Schrider, who coordinates the care management program at
Alta Bates Summit Medical Center in Oakland stated in a Kaiser Health News article:

“Everybody meant well. But she was being referred to three different substance abuse clinics and
two different mental health clinics, and she had two case management workers both working on
housing. It was not only bad for the patient, it was also a waste of precious resources for both
hospitals.”

In order to prevent future situations like this from happening, Alameda county hospitals came
together to create a program called PreManage ED, which shares patient records between
emergency departments.

This system lets the ER staff know things like:

 If the patient they are treating has already had certain tests done at other hospitals, and what
the results of those tests are.

42
  If the patient in question already has a case manager at another hospital, preventing
unnecessary assignments.
 What advice has already been given to the patient, so that a coherent message to the
patient can be maintained by providers.

This is another great example where the application of healthcare analytics is useful and needed.
In the past, hospitals without PreManage ED would repeat tests over and over, and even if they
could see that a test had been done at another hospital, they would have to go old school and
request or send long fax just to get the information they needed.

13) Smart Staffing & Personnel Management

Without a cohesive, engaged workforce, patient care will dwindle, service rates will drop, and
mistakes will happen. But with big data tools in healthcare, it’s possible to streamline your staff
management activities in a wealth of key areas. By working with the right HR analytics, it’s
possible for time-stretched medical institutions to optimize staffing while forecasting operating
room demands, streamlining patient care as a result.

Too often, there is a significant lack of fluidity in healthcare institutions, with staff distributed in
the wrong areas at the wrong time. This imbalance of personnel management could mean a
particular department is either too overcrowded with staff or lacking staff when it matters most,
which can develop risks of lower motivation for work and increases the absenteeism rate. An
HR dashboard, in this case, may help:

Though data-driven analytics, it’s possible to predict when you might need staff in particular
departments at peak times while distributing skilled personnel to other areas within the
institution during quieter periods.

Moreover, medical data analysis will empower senior staff or operatives to offer the right level of
support when needed, improve strategic planning, and make vital staff and personnel
management processes as efficient as possible.

14) Learning & Development

Expanding on our previous point, in a hospital or medical institution, the skills, confidence, and
abilities of your staff can mean the difference between life and death. Naturally, doctors and
surgeons are highly skilled in their areas of expertise. But most medical institutions have a range
of people working under one roof, from porters and admin clerks to cardiac specialists and brain
surgeons.

In healthcare, soft skills are almost important as certifications. To keep the institution running at
optimum capacity, you have to encourage continual learning and development. By keeping track
of employee performance across the board while keeping a note of training data, you can use
healthcare data analysis to gain insight on who needs support or training and when. If everyone is
able to evolve with the changes around them, you will save more lives — and medical data
analytics will help you do just that.

15) Advanced Risk & Disease Management

Big data and healthcare are essential for tackling the hospitalization risk for specific patients with
chronic diseases. It can also help prevent deterioration.

43
By drilling down into insights such as medication type, symptoms, and the frequency of medical
visits, among many others, it’s possible for healthcare institutions to provide accurate
preventative care and, ultimately, reduce hospital admissions. Not only will this level of risk
calculation result in reduced spending on in-house patient care, but it will also ensure that space
and resources are available for those who need it most. This is a clearcut example of how
analytics in healthcare can improve and save people’s lives.

As a result, big data for healthcare can improve the quality of patient care while making the
organization more economically streamlined in every key area.

16) Suicide & Self-Harm Prevention

Globally, almost 800,000 people die from suicide every year. Plus, 17% of the world’s
population will self-harm during their lifetime. These numbers are alarming. But while this is a
very difficult area to tackle, big data uses in healthcare are helping to make a positive change
concerning suicide and self-harm. As entities that see a wealth of patients every single day,
healthcare institutions can use data analysis to identify individuals that might be likely to harm
themselves.

In a 2018 study from KP and the Mental Health Research Network, a mix of EHR data and a
standard depression questionnaire identified individuals who had an enhanced risk of a suicide
attempt with great accuracy. Utilizing a predictive algorithm, the team found that suicide
attempts and successes were 200 times more likely among the top 1% of patients flagged
according to specific datasets. Speaking on the subject, Gregory E. Simon, MD, MPH, a senior
investigator at Kaiser Permanente Washington Health Research Institute, explained:

“We demonstrated that we can use electronic health record data in combination with other tools
to accurately identify people at high risk for suicide attempt or suicide death.”

This essential use case for big data in the healthcare industry really is a testament to the fact that
medical analytics can save lives.

“If somebody tortures the data enough (open or not), it will confess anything.” – Paolo
Magrassi, former vice president, research director, Gartner.

17) Improved Supply Chain Management

If a medical institution’s supply chain is weakened or fragmented, everything else is likely to
suffer, from patient care and treatment to long-term finances and beyond. That said, the next in
our big data in healthcare examples focus on the value of analytics to keep the supplychain
fluent and efficient from end to end.

Leveraging analytics tools to track the supply chain performance metrics, and make accurate,
data-driven decisions concerning operations as well as spending can save hospitals up to $10
million per year.

Both descriptive and predictive analytics models can enhance decisions for negotiating pricing,
reducing the variation in supplies, and optimizing the ordering process as a whole. By doing
so, medical institutions can thrive in the long term while delivering vital treatment to patients
without potentially disastrous delays, snags, or bottlenecks.

44
18) Developing New Therapies & Innovations
The last of our healthcare analytics examples centers on working for a brighter, bolder future in
the medical industry. Big data analysis in healthcare has the power to assist in new therapy and
innovative drug discoveries. By utilizing a mix of historical, real-time, and predictive metrics as
well as a cohesive mix of data visualization techniques, healthcare experts can identify potential
strengths and weaknesses in trials or processes.

Moreover, through data-driven genetic information analysis as well as reactionary predictions in

patients, big data analytics in healthcare can play a pivotal role in the development of
groundbreaking new drugs and forward-thinking therapies. Data analytics in healthcare can
streamline, innovate, provide security, and save lives. It gives confidence and clarity, and it is the
way forward.

How To Use Big Data In Healthcare

All in all, we’ve noticed three key trends through these 18 examples of healthcare analytics: the
patient experience will improve dramatically, including quality of treatment and satisfaction
levels; the overall health of the population can also be enhanced on a sustainable basis, and
operational costs can be reduced significantly.

Let’s have a look now at a concrete example of how to use data analytics in healthcare:

a) Big Data In Healthcare Applied On A Hospital Dashboard

This healthcare dashboard below provides you with the overview needed as a hospital director or
as a facility manager. Gathering in one central point all the data on every division of the hospital,
the attendance, its nature, the costs incurred, etc., you have the big picture of your facility, which
will be of great help to run it smoothly.

b) Big Data Healthcare Application On Patients' Care

Another real-world application of healthcare big data analytics, our dynamic patient dashboard is
a visually-balanced tool designed to enhance service levels as well as treatment accuracy across
departments

Why We Need Big Data Analytics In Healthcare

There’s a huge need for big data in healthcare as well, due to rising costs in nations like the
United States. As a McKinsey report states: “After more than 20 years of steady increases,
healthcare expenses now represent 17.6 percent of GDP — nearly $600 billion more than the
expected benchmark for a nation of the United States’s size and wealth.”

In other words, costs are much higher than they should be, and they have been rising for the past
20 years. Clearly, we are in need of some smart, data-driven thinking in this area. And current
incentives are changing as well: many insurance companies are switching from fee- for-service
plans (which reward using expensive and sometimes unnecessary treatments and treating large
amounts of patients quickly) to plans that prioritize patient outcomes

As the authors of the popular Freakonomics books have argued, financial incentives matter – and
incentives that prioritize patients' health over treating large amounts of patients are a good thing.
Why does this matter?

45
Well, in the previous scheme, healthcare providers had no direct incentive to share patient
information with one another, which had made it harder to utilize the power of analytics. Now
that more of them are getting paid based on patient outcomes, they have a financial incentive to
share data that can be used to improve the lives of patients while cutting costs for insurance
companies.

Finally, physician decisions are becoming more and more evidence-based, meaning that they rely
on large swathes of research and clinical data as opposed to solely their schooling and
professional opinion. As in many other industries, data gathering and management are getting
bigger, and professionals need help in the matter. This new treatment attitude means there is a
greater demand for big data analytics in healthcare facilities than ever before, and the rise of
SaaS BI tools is also answering that need.

Obstacles To A Widespread Big Data Healthcare

One of the biggest hurdles standing in the way to use big data in medicine is how medical data is
spread across many sources governed by different states, hospitals, and administrative
departments. The integration of these data sources would require developing a new infrastructure
where all data providers collaborate with each other.

Equally important is implementing new online reporting software and business intelligence
strategy. Healthcare needs to catch up with other industries that have already moved from
standard regression-based methods to more future-oriented like predictive analytics, machine
learning, and graph analytics.

However, there are some glorious instances where it doesn’t lag behind, such as EHRs
(especially in the US.) So, even if these services are not your cup of tea, you are a potential
patient, and so you should care about new healthcare analytics applications. Besides, it’s good
to take a look around sometimes and see how other industries cope with it. They can inspire you
to adapt and adopt some good ideas

2.4 ELECTRONICHEALTHRECORD(EHR)

 Electronic health record, is the electronic versionof the client data found in the
traditional paper record.
 EHRs are defined as “a longitudinal electronic recordof patient health information
generated by one or more encounters in any care delivery setting.

ROLES OF HER
REPRESENTS patient’s health history
 Medium of Communication among health carepractitioners
 Legal document for health care
 Source for clinical outcomes and healthservices
research
 Resource for practitioner education
 Alerts, reminders, quality improvement

46
 DATACOMPONENTS DOCUMENTEDINEHR

An electronic health record should contain important data such as;

 Patient profile and demographics

 Medical history includes information about allergies, illness,immunization, disorder and
diseases.
 Medicine taken and its compatibility with druginteraction
 Records of appointment
Data components documented in EHRs:
 admission nursing note,
 daily charting,
 physical assessment,
 present complaints (e.g. symptoms),
 diagnoses, tests, procedures, treatment,
 nursing care plan,
 medication administration, progress notes
 laboratory data, and radiology reports
 referral,
 Discharge history,
 Billing recordsCOMPONENTS OF HER

CLINICAL DECISION SUPPORT SYSTEM (CDSS),

 Computerized physician order entry(CPOE)
systems, and
 Health information exchange (HIE).

CLINICALDECISIONSUPPORTSYSTEM(CDSS)

 A CDS system is a software that assists theprovider in making decisions with regard to
patient care.
 CDSS provides physicians and nurses with real-time diagnostic and treatment
recommendations.

FUNCTIONS OF CDSS

 Managing clinical complexities

 Monitoring medication errors

47
  Avoiding duplicate and unnecessary tests
 Supporting clinical diagnosis &Treatment plan processes
 Promoting use of best practices & condition specificguidelines
 Population based management.
 providing the latest information about a drug,
 cross-referencing a patient allergy to a medication, and
 alerts for drug interactions and other potential patient issues

Patient safety with HER

Researchers found that computerized physician reminders increased the use of influenza and
pneumococcal vaccinations from practically 0%to 35% and 50%, respectively, for hospitalized
patients.

Prevention of complicationwith EHR

Willson et al, found a significant association between computerized reminders and pressure
ulcer prevention in hospitalized patients.
They found a 5% decrease in the development of pressure ulcers 6 months after the
implementation of computerized reminders that targeted hospital nurses.

COMPUTERIZED PHYSICIAN ORDER ENTRY(CPOE)

CPOE is a software that allow physicians to enterorders directlyinto the computer rather than doing so
on paper.
Example
 drugs,
 laboratory tests,
 radiology,
 physical therapy

Benefits of CPOE

 Eliminates potentially dangerousmedical errors caused by poor penmanship of physicians.

 Eliminate errors caused by uncleartelephone orders
 It also makes the ordering process more efficient because nursing andpharmacy staffs do
not need to seekclarification or to solicit missing information from illegible or incomplete
orders.

48
  Enhances patient safety

Evidence
 Studies suggest that serious medication errors can be reduced by 55% when a CPOE
system is used alone, and by83% when coupled with a CDS system thatcreates alerts
based on what the physicianorders.
 Using a CPOE system, especially when it islinked to a CDS, can result in improved
efficiencyand effectiveness of care.

HEALTH INFORMATION EXCHANGE

Figure 2.6 Healthinformationexchange

HIE is the process of sharing patient’s electronic health information between different organizations
and can create many efficiencies inthe delivery of health care as shown in figure 2.6
Once health data are available electronicallyto providers, EHRs facilitate the sharing of patient
information through HIE.

Health information exchange-Benefits

 Allows for the secure and potentially real-time sharing of patient information,
 HIE can reduce costly redundant tests
 HIE facilitates the exchange of this information via EHRs, which can result in much more
cost-effective and higher- quality care.

Technologies involved in EHR

 Picture archiving and communications system

 Bar coding

49
  Radio frequency identification
 Automated dispensing medicines
 Electronic medication administration records
Picture archiving and communications ystem:

This technology captures and integrates diagnostic and radiological imagesfrom various devices,
stores them, and disseminates them to a medical record, a clinical data repository, or other points
of care.
e.g., x-ray, MRI, computed tomography scan
Bar coding : An optical scanner is used to electronically capture information encoded on a
product Initially, it is used for medication.

2.5 IoT IN HEALTH CARE

 IoT is a combination of hardware and software technology that produces

trillions of data through connecting multiple devices and sensors with the
cloudand making sense of data with intelligent tools

 Anything can be IoT device, if it can transmit and receivedata over the cloud and
designed to process a unique task

Car that automatically senses the wear and tearand self-schedules the maintenance

Train that dynamically calculates arrival times and intimates to waiting passengers

The Learning
 Massive impact on life and business and Global
economy
 There will be a huge influx of data from connected
devices
 Raw, unstructured and unpredictable data

 Challenge to IT system to manage the enormous volume of

data

 Conventional IT system cannot sustain this tremendous

pressure
The Act
 Need innovations in sensor technology Setup an intelligent network
 Superior high performance cloud computing

50
IOT IN HEALTHCARE

IoT in Healthcare is a heterogeneous computing, wirelessly communicating system of apps and

devices that connects patients and health providers to diagnose, monitor, track and store vital
statistics andmedical information as shown in figure 2.7

Few examples of IoT in Healthcare

 Headsets that measure brainwaves

 Clothes with sensing devices

 BP monitors
 Glucose monitors
 ECG monitors
 Pulse oximeters

 Sensors embedded in medical equipment

 dispensing systems,

 surgical robots and device implants

 Any wearable technology device

51
 Figure 2.7 IoT in Health care

WHAT IS TELEHEALTH?

 TeleHealth is the delivery of healthcare services and clinicalinformation to remote locations

 TeleHealth is an FDA approved, HIPPA compliant platform that interactively connects

patients with a nationwide network of licenseddoctors 24/7 using Internet, Internet of Things
(IoT), video chats, smartphones and Electronic Medical Record (EMR) clouds

 TeleHealth is an hour-in-need solution in the 21st century TeleHealth is a new paradigm in

the Healthcareindustry

SERVICES UNDER TELEHEALTH UMBRELLA

 TeleMedicine: Providing a professional consultation to a patient in a remote location or

assisting a primary care physician in rendering a diagnosis. According to the American
Medical Association (AMA), 78% of emergency carecare could be handled efficiently
using TeleMedicine

 TeleMonitoring: Collecting patient data using IoT and sending the data to a healthcare
monitoring agency for remote testing and diagnosis. TeleMonitoringTeleMonitoring
services also include personalized alerts that inform a patient’s patient’s healthcare
provider in times of physical/mental trauma

 TeleSurgery: Enabling the surgeon to perform an operation on a patient from adistant

location using TeleRobotics technology

 Remote Medical Education: Providing medical education to the health care service
community and targeted groups from a geographically different locationlocation

 TeleHealthData Service: Share specialized health information with other Healthservice

providers, the education industry, research firms, and the government etc.

52
BENEFITS OF TELEHEALTH SERVICES

 Immediate medical attention especially during times of medical emergency

and natural disasters

 No need for waiting in long queues to see a physician

 Eliminate the need to physically go to a medical facility. TeleHealth reduces

thedistance barriers

 Reduced documentation and paperwork

Cost effective – The growth in TeleHealth space will extensively reduce insurance premiums and
potentially reduce the time a patient has to be away from work

Equal and comprehensive healthcare provisions to everyone by eliminatinggeographical barriers

Better communication - Communication to the primary care doctor and specialist happens at the
same time because everyone is virtually present in the same room during diagnosis

Expanded reach to various health service providers

2.6 WEARABLE DEVICES

“Wearable” means whatever a subject can wear, as sweaters, hats, pants, eyeglasses, bras, socks,
watches, patches or devices just fixed on the belt, without encumbering daily activities or
restricting the mobility. The concept of wearability is of particular importance in fields like
monitoring for healthcare, wellbeing and fitness/sport

 Very often wearable technology is based on conventional electronics, either rigid or

bendable, powered by conventional batteries. This includes mobile phone peripherals or
similar, i.e. devices, interfaces or sensors connected to the phone.
 In other cases, wearable technology is more ‘disruptive’ and includes apparel and textiles
with distributed functions, in which electronics is intimately combined. In this case, the
development is not obvious because devices have to be washable, stretchable, foldable,
sometime printable or transparent as shown in figure 2.8

NEW WEARABLES –APPLICATIONS

53
Figure 2.8Wearable Smartphone: Wearable Hybrid Framework for Hand and Foot Gesture

TEXT / REFERENCE BOOKS

1. Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in Health Care
and Biomedicine, Springer-Verlag London 2014.
2. Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionals and
Policymakers. 2016.
3. Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and information
technology professionals. Lulu Press. 2014 Seventh edition.
4. Gaddi A, Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic library holding in the
Health Science Library

54
 SCHOOL OF ELECTRICAL AND ELECTRONICS
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

UNIT – III – eHEALTH – SECA4004

55
UNIT-III DIGITAL HEALTH

Introduction to health care digital transformation- Digital health: Tools, Strategies of digital
health-Technologies in digital health-Implementation of Digital health- Advantages and
challenges of Digital health

3.1 INTRODUCTION TO HEALTH CARE DIGITAL TRANSFORMATION

Value Pathways in Digital Healthcare

 One of the key obstacles to rolling out the Digital Healthcare Ecosystem is bio- medical data
availability, immediacy and liquidity - the flow of clinical data to every stakeholder -
including patients, clinical practitioners, service providers and fund holders.
Manystakeholders are now using “Big Data” methods to overcome this challenge, as part ofa
modern data architecture.
 This section describes some example Digital Healthcare use cases, a Digital Healthcare
reference architecture and how “Big Data” methods can resolve the risks, issues and
problems caused by poor clinical data latency.In January 2013, McKinsey & Company
published a report entitled “The ‘Big Data’ Revolution in Healthcare”. The report points out
how big data is creating value in five “new value pathways” allowing data to flow more
freely between stakeholders.
 The Diagram below is a summary of five of these new value pathway use cases and an
example of how “Big Data” can be used to address each use case. Examples are taken from
the Clinical Informatics Group at UC Irvine Health - many of their use cases are described in
the UCIH case study

Pathway Benefit “Big Data” Use Case

Patient Health Patients can build Predictive Analytics: Heart

and Wellbeing stakeholder valueby patients weigh themselves at
taking an active role in homewith scales that transmit data
their own health, wirelessly to their health center.
wellbeing and Algorithms analyze the data and
treatment, including flag patterns that indicate ahigh
disease risk of readmission, alerting a
prevention. physician.
Patient Patients get the most Real-time Monitoring: Patient
Monitoring timely and appropriate vital statistics are transmitted
diagnoses, treatment from wireless sensors every
and clinical intervention minute. If vital signs cross certain

56
 available. risk thresholds, staff can attend to
thepatient immediately.

Healthcare Healthcare Provider Historical EMR Analysis: Big Data

Provisioning capabilities matched to reduces the cost to store data on clinical
the complexity of the operations, allowing longer retention of
assignment— for data onstaffing decisions and clinical
instance, nurses or outcomes. Analysis of this data allows
physicians’ assistants administrators to promote individuals and
performing tasks that do practices that achieve the best results.
not require a doctor.
Also the specific selection
of the provider with the
best outcomes.
Patient Ensure cost- Medical Device Management: Biomedical
Value effectiveness of care devices stream geo-location and biomedical
Proposition provision, such as tying sensor data to manage patient clinical
Healthcare Provider outcomes from medical equipment. The
reimbursement to patient biomedical team know where all the patients
outcomes, or eliminating and equipment are, so they don’t waste time
fraud, waste,or abuse in searching for a location. Over time,
the system. determine the usage ofdifferent biomedical
devices, and use this information to make
rational decisions about when to repair or
replace equipment.

Digital The identification of Collaborative Research : Clinical

Innovation new therapies and Researchers attached to hospitals can
approaches to delivering access patient data stored in Hadoop
care, across all aspects Cluster “Big Data” Stores for discovery,
of the system and then present the anonymous sample data to
improving Medical their Internal Review Board for approval,
Analytics engines without ever having seen uniquely
themselves. identifiable information.

57
Digital Healthcare

 Changing demographics and regulations are putting tremendous pressure on the healthcare
sector to make significant improvements in care quality, cost control, clinical management,
organizational efficiency and regulatory compliance. To stay viable, it is paramount to
effectively address issues such as missed and mis- diagnosis, coding error, over / under
treatment regimes, unnecessary procedures and medications, insurance fraud, delayed
diagnosis, lack of preventive health screening and proactive health maintenance. To that end,
better collaboration across and beyond the organization with improved information sharing,
and a holistic approach to capture clinical insights across the organization are critical.

 In an environment prevalent with multiple unstructured data silos and traditional analytics
focused on structured data, healthcare organizations struggle to harness 90% of their core
data - which is mostly medical images, biomedical data streams and unstructured free text
found in clinical notes across multiple operational domains. Connecting healthcare
providers directly with patient data reduces risk, errors and unnecessary treatments; thus
enabling better understanding of how delivery affects outcomes - and uncovering
actionable clinical insights in order that proactive and preventive measures decrease the
incidence of avoidable diseases.

 Digital Healthcare is a cluster of new and emerging applications and technologies that
exploit digital, mobile and cloud platforms for treating and supporting patients. The term
is necessarily general as this novel and exciting Digital Healthcare innovation approach is
being applied to a very wide range of social and health problems, ranging from monitoring
patients in intensive care, general wards, in convalescence or at home – to helping doctors
make better and more accurate diagnoses, improving drugs prescription and referral
decisions for clinical treatment.

 Digital Healthcare has evolved from the need for more proactive and efficient healthcare
delivery, and seeks to offer new types of prevention and care at reducedcost – using
methods that are only possible thanks to sophisticated technology.

Digital Healthcare Technologies – Bioinformatics and Medical Analytics.

Novel and emerging high-impact Biomedical Health Technologies such as Bioinformatics and
Medical Analytics are transforming the way that Healthcare Service Providers can deliver Digital
Healthcare globally – Digital Health Technology entrepreneurs, investors and researchers
becoming increasingly interested in and attracted to this important and rapidly growing Life
Sciences industry sector. Bioinformatics and Medical Analytics utilises Big Data / Analytics to
provide actionable Clinical insights.

 Case Study 1 – HP Autonomy Medical Analytics. Changing healthcare service

provisioning, regulation and patient demographics are putting increasing pressure on the
healthcare industry to make significant improvements in care quality, cost management,
organizational efficiency and compliance. Priorities include the need to address
challenging issues such as misdiagnosis, coding error, over / under treatment,
unnecessary procedures and medications, fraud, delayed diagnosis, lack of preventive
screening and proactive health maintenance. Improved collaboration within the

58
 organization with better information sharing, and a holistic approach to capture and action
medical insights across the organization are crucialto success.

 Case Study 2 – Telefónica Digital was created as a Special Purpose Vehicle to lead
Telefónica’s transformation into an M2M / M2C / C2C Digital Services provider - cloud
computing / digital telecommunications value added network services (VANS).
Telefónica Digital is the vehicle for launch / bringing to market digital products and
services - which will help to improve the lives of customers by leveraging the power of
digital technology. This ranges from developing new technologies for healthcare providers
to communicate with other stakeholders, to helping Healthcare Providers, Life Sciences
businesses and government HealthDepartments discover actionable clinical insights,
address new opportunities as shown in figure 3.1 and Table 3.1

The Cone™ - Patient Types

Biomedical Analytics
Hybrid Cone – 3 Dimensions
Presentation

Biomedical Profile

Figure 3.1Biomedical Epidemiology – Groups (Streams), Types (Segments)

59
Table 3.1 TheCone™- Eight Primitives

Primitive Domain Function Product

Who ? People - Patient EMR SalesForce.com

What ? Event Appointment, Walk-in, Primary Care, GPs

Referral, 1st Responders and HealthcareProvider
Emergency Services Hospitals, Clinics

Why ? Motivation Triage - Acute / Chronic Biomedical

Analytics

Where ? Places - Location GIS / GPS / Analytics Geospatial Analytics

When ? Time / Date Procedure Biomedical

Analytics

How ? Biomedical Data Streaming Medical Data Smart Devices /

AppsMobile
Platforms, IoT
Which ? Clinical Procedure Investigate, Nurse, Consultant
Diagnose,Treatment,
Follow-up
Via ? Referral Channel Healthcare Service Healthcare Provider
Delivery Partner Delivery, Procedure Hospitals, Clinics

Data Dimension

60
3.2 DIGITAL HEALTH: TOOLS, STRATEGIES OF DIGITAL HEALTH

Data Science in Digital Healthcare

Figure 3.2 Data science in Digital Health care

These are some of the most important DIGITAL HEALTH CATEGORIES...as shown in
figure 3.2.
 Digital Imaging – (MRI / CTI / X-Ray / Ultrasound)
 Robotic Surgery – (Microsurgery / Remote Surgery)
 Patient Monitoring – (Clinical Trials / Health / Wellbeing)
 Biomedical Data – (Data Streaming / Biomedical Analytics)
 Emergency Incident Management – (Response Team Alerts)
 Epidemiology – (Disease Transmission / Contact Management)

Here are some of the most important DIGITAL MONITORING SMART APPS.....
 Activity Monitor – (Pedometer / GPS)
 Position Monitor – (Falling / Fainting / Fitting)
 Sleep Monitor – (Light Sleep / Deep Sleep / REM)
 Cardiac Monitor – (Heart Rhythm / Blood Pressure)

61
  Blood Monitor – (Glucose / Oxygen / Liver Function)
 Breathing Monitor – (Breathing Rate / Blood Oxygen Level)

Digital Healthcare – Executive Summary

 Digital Healthcare is a cluster of new and emerging applications and technologies that exploit
digital, mobile and cloud platforms for treating and supporting patients. The term "Digital
Healthcare" is necessarily broadand generic as this novel and exciting Bioinformatics and
Medical Analytics innovation driven approach is applied to a very wide range of social and
health problems - from monitoring patients in intensive care, general wards, in convalescence
or at home – to helping general practitioners make better informed and more accurate
diagnoses, improving the effect of prescription and referral decisions for clinical treatment.

 Bioinformatics and Medical Analytics utilises Data Science to provide actionable clinical
insights. Digital Healthcare has evolved from the need for more proactive and efficient
healthcare service delivery, and seeks to offer new and improved types of pro- active and
preventive monitoring and medical care at reducedcost – using methods that are only possible
thanks to emerging SMAC Digital Technology.

Digital Healthcare Technologies – Bioinformatics and Medical Analytics: -

 Digital Patient Monitoring
 Biomedical Data Streaming
 Biomedical Data Science and Analytics
 Epidemiology, Clinical Trials, Morbidity and Actuarial Outcomes

 Novel and emerging high-impact Biomedical Health Technologies such as

Bioinformatics and Medical Analytics are transforming the way that Healthcare Service
Providers can deliver Digital Healthcare globally
 Digital Health Technology entrepreneurs, investors and researchers becoming
increasingly interested inand attracted to this important and rapidly expanding Life
Sciences industry sector.

 While many industries can benefit from SMAC digital technology – Smart Devices, Mobile
Platforms, Analytics and the Cloud – this is especially the case for Life Sciences, Pharma
and Healthcare industry sectors – resulting in more accurate diagnosis, improved treatment
regimes, more reliable prognosis, better patient monitoring, care and clinical outcomes. Let’s
take a look at some of the Digital Technologies that are bringing significant improvements
and benefits to Healthcare

 Today, thanks to the regulatory compliance requirements for HIPAA, HITEC, PCI DSS and
ISO 27001, the reluctance to adopt Digital Technology has been overcome, and Digital
Healthcare adoption is gaining increased traction. Many of the security features required for
data protection and patient confidentiality are being addressed by Digital Healthcare service
providers, therefore relievinghealthcare delivery organizations from tedious and complex
security and data protection frameworks.

62
Biomedical Data Analytics:
The exploitation of data by applying analytical methods such as statistics, predictive and
quantitativemodels to patient segments or groups of the population will provide better insights and
achieve betteroutcomes. As far back as 2010, there was evidence that: “93 percent of healthcare
providers identified the digital information explosion as the major factor which will drive
organizational change over the next 5 years.”

Data Security and Privacy:

Today, thanks to the regulatory compliance requirements for HIPAA, HITEC, PCI DSS and ISO
27001, reluctance to adopt emerging technologies is starting to be addressed and digital technology
is beginning to gain traction - bear in mind also that many of the security features required for data
security and protection are addressed by the service providers, therefore relieving the healthcare
organization from tedious and complex security frameworks.

Mobility:
Mobility Services, where Smart Devices, Smart Apps, Mobile Platforms and Cloud Infrastructure is
providing the backbone for medical personnel to access all sorts of patient information from any
place, any where - and from a wide range of mobile devices.

Collaboration with patients:

Mobility means that complete patient records are now available to healthcare professionals
anytime, anywhere – allowing physicians to access historical patient case records , images and
clinical data to fine-tune their diagnosis and make informed decisions on treatment – thus
reducing diagnosis latency, increasing accuracy and improving patient care and clinical outcomes
from initial consultation to specialist referrals. Some scenarios are illustrated in the following: -

Physician Collaboration Solutions (PCS) •

 PCS solutions offers video conferencing to facilitate remote consultations and care
continuity, allowing patients to be viewed remotely. PCS allows physicians to consult
withpatients and even perform remote robotic surgery. This is dubbed “tele-health
solutions.”
Electronic Medical Records (EMR) •
 Every piece of information pertaining to a specific is recorded and stored. The solution
is designed to capture and provide a patient’s data at any time of the patient’s
monitoring cycle, including the complete medical records and history.

Patient Information Exchange (PIE) •

 This allows for the healthcare information to be shared electronically across
organizations within a region, community or hospital system. There are currently
several Digital Healthcare cloud service providers addressing this market, taking the
role of collecting and distributing medical information from and among multiple
organizations.

 The New York Times has published an interesting article illustrating the use of the
cloudin healthcare - leveraging big data in the cloud to manage patient relationships
and clinical outcomes.

63
Collaboration among peers:
Technology can provide medical assistance to doctors in the field, b e it in remote areas orin
emergency relief operations through satellite communications. Refer to the Remote Assistance
for Medical Teams Deployed Abroad (T4MOD project) which could easily findits place in the
Digital Healthcare cloud space.

3.3 BIG DATA IN DIGITAL HEALTHCARE

“Big Data” in Pharma / Life Sciences

Big data now plays an important role in medical and clinical research. Digital Patient Records are
now being harvested and analysed in large-scale patient population studies – which are yielding
actionable clinical insights. The UK Government has made anonymised patient records from the
National Health Service openly available. Medical Centres, Research Institutes and Pharma /Life
Sciences funding agencies have all made major investments in this area.

SENSE LAYER – Remote Monitoring and Control – WHAT and WHEN?

 Remote Sensing – Sensors, Monitors, Detectors, Smart Appliances / Devices

 Remote Viewing – Satellite. Airborne, Mobile and Fixed HDCCTV
 Remote Monitoring, Command and Control – SCADA

GEO-DEMOGRAPHIC LAYER – People and Places – WHO and WHERE?

 Person and Social Network Directories - Personal and Social Media Data
 Location and Property Gazetteers - Building Information Models (BIM)
 Mapping and Spatial Analysis – Landscape Imaging & mapping, Global Positioning
(GPS)Data
 Temporal / Geospatial data feeds –Weather and Climate, Land Usage, Topology / Topography

INFORMATION LAYER – “Big Data” and Data Set “mashing” – HOW and WHY?

 Content – Structured and Unstructured Data and Content

 Information – Atomic Data, Aggregated, Ordered and Ranked Information
 Transactional Data Streams – Smart Devices, EPOS, Internet, Mobile
Network

64
SERVICE LAYER – Real-time and Predictive Analytics – WHAT / WHEN NEXT?
 Global Mapping and Spatial Analysis - GIS
 Service Aggregation, Intelligent Agents and Alerts
 Data Analysis, Data Mining and Statistical Analysis
 Optical and Wave-form Analysis and Recognition, Pattern and Trend Analysis an
Extrapolation

COMMUNICATION LAYER – Mobile Enterprise Platforms and the Smart Grid

 Connectivity - Smart Devices, Smart Apps, Smart Grid
 Integration - Mobile Enterprise Application Platforms (MEAPs)
 Backbone – Wireless and Optical Next Generation Network (NGE) Architectures

INFRASTRUCTURE LAYER – Cloud Service Platforms

 Public, Mixed / Hybrid, Enterprise, Private, Secure and G-Cloud Cloud Models
 Infrastructure – Network, Storage and Servers
 Applications – COTS Software, Utilities, Enterprise Services
 Security – Principles, Policies, Users, Profiles and Directories, Data Protection

DIGITAL HEALTH CARE –CLUSTER THEORY

Figure 3.3 Cluster Theory

Medical Education and Remote Diagnostics
Capabilities in Remote Diagnostics and Medical Education are evolving rapidly. Companies that
are innovating on this front and encompassing solutions such ascrowd-sourcing and peer- 2-peer
65
learning. Some of those companies really taking advantage of the explosion in Biomedical “Big
Data' include HP, GE Healthcare, Siemens Healthcare, Boardvitals and AgileM as shown in
figure 3.3

Secure Storage and Sharing of Biomedical Information

Box is a platform that is HIPAA and HITECH compliant for secure capture, storage and
management of Protected Personal Health Information (PPHI).

Medical Service Provider's Tools

 More and more service providers continue to jump on board with the new Medical
Service Provider's Tools that are out there.
 Two companies that are particularly interesting are Clinicast and Reify Health (currently in
beta test)

3.4 DIGITAL DIAGNOSTICS TOOLS

 Researchers are now taking advantage of new and emerging biomedical technologies
which integrate with Mobile Phones and other Smart Devices in orderto add diagnostic
capabilities to the arsenal of the general and clinical physician. One company that looks
promising in the future is Cellscope - FDA approved.

 Proteus Digital Health takes endoscopy to an extraordinary new level. This device is
housed in a small capsule which can be swallowed - and contains a range of sensors and
detectors, automatically streaming continuous digital information – and even images - to
Mobile Phones and other Smart Devices. The device is capable of monitoring and tracking
how the patient’s alimentary canal anddigestive system behaves when an oral drug is
being administered or when food ordrink is being consumed. Nephosity - imaging - FDA
approved.

 Dexcom markets a device that monitors blood glucose levels which is tucked neatly under
the skin of the patient’s abdomen - FDA approved. Google are trialling a soft contact lens
with an embedded bluetooth device and a sensor that monitors blood glucose levels -
which continuously streams blood glucose level data to a monitoring service in the cloud,
via a bluetooth mobile phone connection.

Patient Communities – Chronic Disease Management

 Reducing the cost of treating chronic illness is a major goal – because it can
dramatically improve health indices in populations of individuals suffering fromchronic
long-term illness Focusing on those highest-cost patient population'sis an exciting
approach thata number of companies are exploring. Chronic Disease management can be
improved by supporting care providers and extenders that take on the task of assisting
with the healthcare and improving the outcomes of these high-cost patients.

 Patients that have chronic illness have a variety of needs. Some patients require planned,
regular interactions with support to their carers, focusing on function and prevention of
acute episodes and complications. Community Healthcare Coaches can provide ongoing
assessments in compliance with the treatment plan. Another important issue could be
behavioural modification, and an organised support system for the patient

66
Electronic Medical Records (EMR's)

 EMR's are Active web applications that can intervene directly in order to effect positive
patient outcomes. “Prioritising positive patient care becomes a naturalconsequence when the
EMR is built with the intent of facilitating the patient- physician relationship. EMR's focus
on supporting the physician – so that the physician can focus on treating the patient” - says
Kyna Fong - ElationEMR

 Companies developing Active Patient Management in order to promote positive Medical

Outcomes include the following Digital Health Technology providers: -

 ElationEMR, GEHealthcare, Curemd and Drchrono and 5 O'Clock Records, CareCloud

between them offer a variety of web-based EMR‘s in addition to General Practice patient
administration systems and revenue cycle management solutions

 DoseSpot is an e-prescribing platform. Medopad and Practice Fusion are EMR's which are
marketed to community practitioners and doctors in primary health groups.

Telemedicine
 With systems such as Teladoc you can obtain an on-line consultation froma consultant
physician or specialist anywhere in the world via an on-line video-link. Teladoc is
bringing this facility over to the 'brick and mortar' side by working on the development of
walk-in patient kiosks situated in Health Centres and high-street Pharmacies .

Grid Computing World

 Community Grid for grid computing applications - Mobile Phones and other smart devices
will make use of sensor and imaging technology to gather passive and active data for
statistical analysis and diagnosis via Remote Healthcare Monitoring and Emergency Event
Management Centres.

Care Delivery
 Delivery of care can always be improved. Some of the winners in this category are going
to be: -

 –One Medical, Sherpaa, Metamed (personalized medical research) and Statphone (patient
transfers)

67
Behavioural Health Analytics
Patient Behaviour Analysis is the diagnostic tool of the future. Every patient has unique genetic
characteristic and environmental exposure - habits and behaviour patterns - and any changes to
those everyday habits and behaviour patterns may be an indicator of a change in health status
requiring intervention or a predictive determinant of the future path a patient may take in terms
of health and wellbeing.Mobile Phones and other smart devices will make use of sensor and
imaging technology to gather passive and active data for statistical analysis and diagnosis.

Biomedical “Big Data” Management and Analytics

 Anapsis and EMBI, focus on Biomedical “Big Data” Management and Analytics. This
service is highly customisable for every client.

 Ginger.io is another example of a Behavioural Analytics platform. Ginger.io examines

patterns of everyday activity which are used as points of entry for understanding larger issues
such as paediatrics requirements, geriatrics needs and mental health care for schemes such as
Care in the Community and AssistedLiving at Home.

Transitional Care
 "Care transitions" is a term that describes the flow of patients from clinical settings to
settings in the community - which are socially more appropriate relative to their needs.
Every patient's needs change over time. Patients mayencounter a Primary Care Provider, a
hospital physician, the nursing team and even Social Services before they are “whisked
off" to a nursing facility or care home. Promising companies in the area of Care Transition
include: -Care At Hand, Independa and OpenPlacement

 Companies such as these are building Smart Apps for Mobile Phones and other smart
devices which will make use of sensor and imaging technology for streaming data to
monitoring services that will bring new possibilities in the transition from Intensive Care
Units and General Hospital Wards, into a convalescent nursing facility or care home and
on into other patient care schemes such as Care in the Community and Assisted Living at
Home.

Patient Management and Patient Administration Systems

 Integrated new clinical and back-office Patient Management and Patient

Administration Systems will be in demand to manage the changing landscape of
healthcare services provisioning, funding and cross-charging.

 Some of the challenges that are being addressed range from the simple capture at source of
one-off chargeable consultation, medication and point medical procedures – to fully-
featured clinical billing systems for managing the provision of complex multi-stage and
continuous medication and clinical procedures, re-charging costs and administering
payments from Primary Carebudget holders and Health Insurance Companies – or patients
themselves.

 Solutions from those companies listed below are of interest: -

68
  Medmonk, Medikly, Simplee, Cake Health, Castlight Healthcare, SwiftPayMD.

WAVE-FORM ANALYTICS - an analytical tool based on Time-frequency Wave- form

analysis – which has been “borrowed” from spectral wave frequency analysis in Physics.
Deploying the Wigner-Gabor-Qian (WGQ) spectrogram – a method which exploits wave
frequency and time symmetry principles – demonstrates a distinct trend forecasting and analysis
capability in Wave-form Analytics. Trend-cycle wave-form decomposition is a critical technique
for testing the validity of multiple (compound) dynamic wave-series models competing in a
complex array of interacting and inter- dependant cyclic systems - waves driven by both
deterministic (human actions) and stochastic (random, chaotic) paradigms in the study of
complex cyclic phenomena.

WAVE-FORM ANALYTICS in “BIG DATA - characterised as periodic alternate sequences

of, high and low trends regularly recurring in a time-series – resulting in cyclic phases of
increased and reduced periodic activity – Wave-form Analytics supports an integrated study of
complex, compound wave forms in order to identify hidden Cycles, Patterns and Trends in Big
Data. The existence of fundamental stablecharacteristic frequencies in large aggregations of time-
series Economic data sets (“Big Data”) provides us with strong evidence and valuable
information about the inherent structure of Business Cycles. The challenge found everywhere in
business cycle theory is how to interpret very large scale / long period compound-wave
(polyphonic) temporal data sets which are non-stationary (dynamic) in nature.

BIOMEDICAL DATA SENSORS AND DETECTORS

Data Captured via Biomedical sensors, detectors, metering (measurement), monitoring (looking
for changes) and control (maintaining vital statistics) systems - can now be managed in vast
“Biomedical Clouds” which exploit grid computing devices in order to capture, store and
interrogate a wide spectrum of real-time Biomedical Data Types – ranging from simple
measurements of patients temperature, blood oxygen, sugar and carbon dioxide levels – to the
most complex Image Processing and Visual Rendering in real time using data streamed from
MRI, CTI, Ultra-sound and X-ray scanning machines as shown in figure 3.4 and 3.5

69
 Figure 3.4 and 3.5 Data turbine cloud
There are three major areas of opportunity – these are some of the applications that Biomedical
companies are currently working on: -

 Biomedical data collection, storage and communication - from individual patients

 Biomedical data integration – combining multiple data sets for analysis / interpretation
 Biomedical data aggregation and summarisation – vast clinical data sets collected and
integrated from thousands of patients – driving Geo-demographic clustering and statistical
analysis for Clinical Trials, Epidemiology, Morbidity and Actuarial Science

70
  Companies that have great potential in these areas include: - Sanyo Intelligence, Apple and
GEHealthimagination, Cardiio, MC10, AliveCor, AgaMatrix, Proteus

Real-time Biomedical Data Streaming

Biomedical Scientists around the world are deeply committed to advanced Medical Programmes
which are capable of automatically generating and processing, Exobytes (millions of Petabytes) of
Biomedical Data. in real-time This data is captured via Biomedical, sensors, detectors, measurement,
monitoring and control systems - and is managed in vast “Biomedical Clouds” which utilise grid
computing devices in order to capture, store and analyse a wide spectrum of real-time Biomedical
Data Types – ranging from simple measurements of patients temperature, blood oxygen, sugar and
carbon dioxide levels – to complex Image Processing and Visual Rendering in real time using data
from MRI, CTI, Ultra-sound and X-ray scanning machines

REAL-TIME BIOMEDICAL DATA STREAMING (RIMES)

Real-time Biomedical Data Streaming

 Most of these Biomedical datasets are huge – potentially containing Exobytes (millions of
Petabytes ) of Biomedical “Big Data”. Biomedical Data Streams are composed of machine-
generated metering, sensing and monitoring data captured by scientific instruments deployed
in support of large-scale Biomedical Research programs. Biomedical Software features
intelligent agents and alerts which can automatically trigger alarms and interventions.
Various types of biomedical data are supported by the Biomedical Cloud environment,
including .pdb and .dcd files.

 As Biomedical Data in the working repository is continuously updated, appended image

frames may be streamed to an RBNB Data-turbine Cloud by the RIMES Synchronisation
client - which ensures that data from the Biomedical Data Stream is continuously
synchronized with the Biomedical Data Cloud. User Clinicians may deploy various extended
user services over the core biomedical grid computing features and mass storage

 systems – including various Biomedical Software Portals,such as intelligent agents and

alerts, visualization and analytics tools portals – whichare continuously processing
incoming dynamic realtime biomedical data stream

3.5 DIGITAL HEALTH

Hadoop Framework

 The workhorse relational database has been the tool of choice for businesses for well over
20 years now. Challengers have come and gone but the trusty RDBMS is the foundation of
almost all enterprise systems today. This includes almost all transactional and data
warehousing

71
  systems. The RDBMS has earned its place as a proven model that, despite some quirks,
is fundamental to the very integrity and operational success of IT systems around the world.

 The relational database is finally showing some signs of age as data volumes and network
speeds grow faster than the computer industry's present compliance with Moore's Law
cankeep pace with. The Web in particular is driving innovation in new ways of processing
information as the data footprints of Internet-scale applications become prohibitive using
traditional SQL database engines.

When it comes to database processing today, change is being driven by (at least) fourfactors:

 Speed. The seek times of physical storage is not keeping pace with improvements in network
speeds.

 Scale. The difficulty of scaling the RDBMS out efficiently (i.e. clustering beyond a handful of
servers isnotoriously hard.)

 Integration. Today's data processing tasks increasingly have to access and combine data from
manydifferent non-relational sources, often over a network.

 Volume. Data volumes have grown from tens of gigabytes in the 1990s to hundreds of
terabytesandoften petabytes in recent years.

Hadoop Framework

 These datasets would previously have been very challenging and expensive to take on
with a traditional RDBMS using standard bulk load and ETL approaches. Never mind
trying to efficiently combining multiple data sources simultaneously or dealing with
volumes of data that simply can't reside on any single machine (or often even dozens).
Hadoop deals with this by using a distributed file system (HDFS) that's designed to deal
coherently with datasets that can only reside across distributed server farms. HDFS is also
fault resilient and so doesn't impose the overhead of RAID drives and mirroring on
individual nodes in a Hadoop compute cluster, allowing the use of truly lowcost
commodity hardware.

 So what does this specifically mean to enterprise users that would like to improve their
data processing capabilities? Well, first there are some catches to be aware of. Despite
enormous strengths in distributed data processing and analysis, MapReduce is not good in
some key areas that the RDMS is extremely strong in (and vice versa). The MapReduce
approach tends to have high latency (i.e. not suitable for real-time transactions) compared
to relational databases and is strongest at processing large volumes of write-once data
where most of the dataset needs to be processed at one time. The RDBMS excels at point
queries and updates, while MapReduce is best when data is written once and read many
times.

72
 The story is the same with structured data, where the RDBMS and the rules of database
normalization identified precise laws for preserving the integrity of structured data and
which havestood the test of time. MapReduce is designed for a less structured, more
federated world where schemas may be used but data formats can be much looser and
freeform.

73
 Figure 3.6 Hadoop architecture
Hadoop Framework

 Each of these factors as shown in figure 3.6 is presently driving interest in alternatives that
are significantly better at dealing with these requirements. I'll be clear here: The relational
database has proven to be incredibly versatile and is the right tool for the majority of
business needs today. However, the edge cases for many large-scale business applications
are moving out into areas where the RDBMS is often not the strongest option. One of the
most discussed new alternatives at the moment is Hadoop, a popular open source
implementation of MapReduce. MapReduce is a simple yet verypowerful method for
processing and analyzing extremely large data sets, even up to the multi- petabyte level.
At its most basic, MapReduce is a process for combining data from multiple
inputs(creating the "map"), and then reducing it using a supplied function that will distill
and extract thedesired results. It was originally invented by engineers at Google to deal
with the building of production search indexes. The MapReduce technique has since
spilled over into other disciplinesthat process vast quantities of information including
science, industry, and systems management. For its part, Hadoop has become the leading
implementation of MapReduce.

 While there are many non-relational database approaches out there today (see my
emerging IT and business topics post for a list), nothing currently matches Hadoop for the
amount of attention it's receiving or the concrete results that are being reported in recent
case studies. A quick look at thelist of organizations that have applications powered by
Hadoop includes Yahoo! with over 25,000 nodes (including a single, massive 4,000 node
cluster), Quantcast which says it has over 3,000 cores running Hadoop and currently
processes over 1PB of data per day, and Adknowledge who uses Hadoop to process over
500 million clickstream events daily using up to 200 nodes

TEXT / REFERENCE BOOKS

1. Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in HealthCare and
Biomedicine, Springer-Verlag London 2014.
2. Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionals and
Policymakers. 2016.
3. Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and information
technology professionals. Lulu Press. 2014 Seventh edition.
4. Gaddi A, Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic library holding in the Health
Science Library

74
 SCHOOL OF ELECTRICAL AND ELECTRONICS
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

UNIT – IV– eHEALTH – SECA4004

75
UNIT-IV ARTIFICIAL INTELLIGENCE IN eHealth
History of AI in health care-Impacts and Aspects of AI in health care- Current research in AI in
eHealth-Regulations and Ethical concerns in using AI in eHealth.

4.1 OBJECTIVES

 The symptomatology affecting us is hyper-variable. Current practice guidelines, the variability of

experience in medicine, the translatability and two-way outcome tracking suffers. This can lead
 to sub-optimal handling of the disease. Patient outcome is unpredictable.

 In ‘Machine Learning ’, machine is made to learn the various parameters including, symptoms,
behavior, biochemical and pathologic variables, among others. With help of a specially-
designed software, the computer can develop effective learning.

 AI needs machine-learning, facilitates heightened diagnostic sensitivity, specificity and

treatment.

 SahaManthran proposes a knowledge based initiative around medical virtualism to be utilized

for co-creating machine-learning derived AI in Medicine.

 Innovations in Medical andBiological Engineering

1950s and earlier

 Artificial Kidney
 X ray
 Electrocardiogram
 Cardiac Pacemaker
 Cardiopulmonary bypass
 Antibiotic Production technology
 Defibrillator

 1970s

Computer assisted tomography

 Artificial hip and knee replacement
 Balloon catheter
 Endoscopy
 Biological plant food engineering
1960s
 Heart valve replacement
 Intraocular lens
 Ultrasound
 Vascular grafts
 Blood analysis and processing

76
1980s
 Magnetic resonance imaging
 Laser surgery
 Vascular grafts
 Recombinant therapeutics
Present day
 Genomic sequencing and microarrays
 Positron Emission tomography
 Image guided surgery

New generations of medical technology products are

Combination of different technologies which lead to the crossing of borders between traditional
categories of medical products such as medical devices, pharmaceutical productsor human tissues
as shown in figure 4.1

Figure 4.1 Converging Technologies

77
  Definition--“Use of a computer to model intelligent behaviour with minimal human
intervention”
 Machines & computer programs are capable of problem solving and learning, like a human
brain.
 Natural Language Processing (“NLP”) and translation,
 Visual perception and
 Decision making.
 Machine Learning (“ML”), one of the most exciting areas for Development of
computational approaches to automatically make sense of data
Advantage of Machine
 Can retain information
 Becomes smarter over time
 Machine is not susceptible to Sleep deprivation, distractions, information overload and
short-term memory loss

4.2 ARTIFICIAL INTELLIGENCE AND BIG DATA IN HEALTHCARE

Artificial Intelligence and big data are more commonly used in healthcare every year. With this
article, we will take a closer look at both these disciplines and see the benefits of implementing
Artificial Intelligence and big data in the healthcare industry. We will also go through the history of
Artificial Intelligence and big data in healthcare and its future.
Similarly, as in the pharmacy – Artificial Intelligence is a new trend in the healthcare industry sector
and you can easily say that it’s still in its infancy. When most people hear “Artificial Intelligence in
healthcare” their first thoughts may be related to the Star Wars movies, where there are no human
doctor as shown in figure 4.2. Everything related to healthcare is done by intelligent robots and
systems. Is this our future? Well, probably. But we are still far away from that. Let’s stick to the
Earth.

ARTIFICIAL INTELLIGENCE IN HEALTHCARE

We should start at the beginning! What is artificial intelligence in healthcare exactly about? Take
a look at the definition provided by Wikipedia: “is the use of complex

78
algorithms and software to emulate human cognition in the analysis of complicated medical data.
Specifically, AI is the ability for computer algorithms to approximate conclusions without direct
human input”.

Figure 4.2 Intelligence in Humans

To put it in more “human” language – Artificial Intelligence is everything including applications,
systems, algorithms and devices that help human physicians in providing healthcare and is based on
computer analysis and big data. For instance: robot-assisted surgery units, diagnostics algorithms,
drug research algorithms, devices monitoring patient’s body condition and many more. It is hard to
imagine modern medicine without additional artificial intelligence support, even though the way to
its real role in the healthcare industry has “just” started. So long story short: what is artificial
intelligence and big data in healthcare? It’s a necessity.

4.3 HISTORY OF AI IN HEALTHCARE

History of Artificial Intelligence in healthcare is quite short as it needs many modern time
inventions to work, to name just computers and the internet. The first attempts to implement
Artificial Intelligence in healthcare were in the late XX century around the
1970s when Dendral was introduced at the Stanford University, USA. It is assumed to be the very
first Artificial Intelligence in the healthcare system. Originally it was used to help chemists in
identifying unknown organic molecules, by analyzing their mass spectra and using knowledge of
chemistry. Dendral was written in the LISP programming language and was a father for many
following Artificial Intelligence systems in healthcare, to name just the MYCIN – system that used
Artificial Intelligence to identify bacteria as shown in figure 4.3

79
adjusted for patient’s body weight.

Figure 4.3 Bacteria in human

The next milestone happened in around 1990 in the minds of the artificial intelligence systems.
They decided that if AI has to offer any assistance it has to be based on the expertise of
physicians and take into consideration the lack of perfect and vast data. That was necessary for
the following development and improvements of artificial intelligence in healthcare. Since then
much has changed and today Artificial Intelligence in healthcare is much more advanced.

EXAMPLES OF ARTIFICIAL INTELLIGENCE.

 Today, Artificial Intelligence in healthcare brings much more value to the industry.
It is developing rapidly and is predicted to do so, or even faster in the near future. We
will take a look at the future of AI in healthcare, but first, let’s find out what goes on right
now.
 Take a look at some examples of how is Artificial Intelligence used in healthcare and
check what benefits Artificial Intelligence brings to the healthcare industry.
.
EXAMPLES OF ARTIFICIAL INTELLIGENCE IN HEALTHCARE

Diagnostics
One of the examples of Artificial Intelligence in healthcare is diagnostics. We wrote about
that previously in the article about AI in pharmacy. Diagnostics consist of tons of data –
to name just medical imaging analysis, patient medical records, patient treatment history,
patient genetics, and his or her circumstances as shown in figure 4.4

Figure 4.4 Diagnosis with AI

80
 recommending optimal treatment. The best example is the cancer diagnosis. Standard,
radiological methods are not sufficient. As it turns out, traditional radiological
imaging misses signals indicating cancer in about 30% cases! On the other hand,
Artificial Intelligence is much more accurate. In 2013 data scientists from the
KAIST University in South Korea introduced an Artificial Intelligence algorithm called
LUNIT, that’s capable of identifying cancer cells basing on x-rays images and
mammography images to detect lung and breast cancer. Its accuracy was mind-boggling
97% in detecting lung cancer and breast cancer.
According to the Accenture company, automated image diagnosis itself can save a
whopping $3 billion a year

Robot-assisted surgery
 Take a look at another example of Artificial Intelligence in healthcare – robot-assisted
surgery. This is one of the most essential applications of Artificial Intelligence in
healthcare. In this case, there are two main benefits – huge money savings and more
effective surgery. Accenture estimates that AI robot-assisted surgery could save the US
healthcare industry $40 as shown in figure 4.5billion annually by 2026.

Figure 4.5 AI robot assisted surgery

 And what about the surgery itself? Well, as we said, robot-assisted surgery is much more
effective and precise. In 2017 alone there were executed almost 700 000 robot-assisted
procedures. Thanks to its precision and miniaturization, the results are undisputable – smaller
incisions, decreased blood loss, less pain, and quicker healing time. However, there is the
other side of the coin. The robot-assisted procedures are more expensive, as one robotic unit
costs at least $1M, and it takes time to properly train surgeons in using Artificial Intelligence
support. Surgeons have to perform 100-250 surgical procedures in order to use their new
robot assistants with the benefit of the patient*.
 Now you know how is artificial intelligence used in healthcare. Let’s turn to the big data.

81
Big data in health care
 Although big data in healthcare is strictly related to Artificial Intelligence in healthcare,
these two disciplines are not exactly the same thing. To simplify it, think of big data as a
source for Artificial Intelligence. Big data is exactly what powers up the Artificial
Intelligence and allows it to work efficiently.
 When you deal with large amounts of data, at some point it becomes very difficult or even
impossible to master all of those gigabytes. The data scientists are trying to automate the
storage and analysis of these large amounts of data in order to get as many advantages as
possible from them.

 Big data in healthcare consists of billions of entries about patients, treatments, drugs,
surgical procedures, research results, and many more. If you want to use all that data on a
regular basis, you simply have to think of the way to analyze and process it efficiently.
And this is what big data in healthcare is about.
 Now, take a look at the benefits of artificial intelligence and big data in healthcare.
Generally speaking, big data can help in improving patient service, determining and
implementing appropriate methods for patient treatment, supporting clinical treatment or
monitoring efficiency of the healthcare companies. There is much more, but today we will
name and lookcloser to the three most important benefits.

BENEFITS OF BIG DATA IN HEALTHCARE

 Much more improved patient care: thanks to the electronic data records, collecting patient
data is much more effective and easier to use to find the best treatment for the given
patient. Big data helps in collecting demographic and medical data such as lab tests,
clinical data, diagnoses, medical conditions, treatment history, family member’s clinical
data, etc. What’s more, big data can help in the prediction of disease incidence or
detecting trends that lead to better health and lifestyle of society as shown in figure 4.6

Figure 4.6 Big data in Health care

 Improved operational and R&D efficiency. Healthcare companies can cut down on

82
  healthcare costs and provide better care. All that with the help of predictive analysis of the
staff efficiency and patient admissions for example to the hospital. Big data in healthcare
helps in organizing workflow and provide not only better care but also more effective in
terms of the costs. And what about R&D? Big data is supporting work on new drugs and
clinical trials thanks to the ability to analyze all data instead of the selection of the test
samples. Big data also has the ability to identify specific patients with wanted biological
characteristics who will participate in specialized clinical trials.
 Finding a cure for diseases. Big data can help in uncovering earlier unknown disease
correlations, hidden patterns, and insights. All thanks to examining large sets of data to
find new cures for the diseases or prescribe the best treatment. Big data has the possibility
of predicting the occurrence of specific diseases or prognosis of disease progression and
factors determining it.
 Surely, you will agree that the benefits of big data in healthcare are staggering, creating
great new possibilities and perspectives for the future.

FUTURE OF ARTIFICIAL INTELLIGENCE AND BIG DATA IN HEALTHCARE

 Now you know what big data and artificial intelligence look like currently and how they
are helpful in modern medicine. What we should do now is to concentrate on the future as
shown in figure 4.7 What future of artificial intelligence and big data in healthcare is
going to look like?

Figure 4.7 AI using robots for Health care

 Because artificial intelligence is producing great savings (it is estimated that by 2026 it
will save up to $150 billion!). Its development will definitely go on. Firstly, we go back to
the question from the beginning of this article – will machine doctors replace humans? It
is probable. Actually, it happens already – for instance there is almost no need for human
presence in radiology! Artificial algorithms are much more accurate in their judgments
and above all – noticeably faster. When it comes to human life, time is the most important
factor. Just seconds can change everything. So we expect to see a much bigger role of
artificial intelligence in a diagnosis.Another thing – AI systems are “armed” with a lot of
information so they can assist in clinical decision making. And their role in that part of
medicine will go sky-high in no time. The minimization of diagnostic errors and
therapeutic errors .

83
  Future doctors will base their work and judgments almost entirely on artificial
intelligence. To sum up this part we might say that the future of artificial intelligence
and big data inhealthcare is full of great perspectives and fantastic potential!
 That happens already, but shortly they will be much more advanced and
complicated. Imagine Google Assistant telling you it is time to do your blood tests. Or
even doing these tests by itself through your smartwatch. Healthcare apps will be
something more than they are now. They will act as a personal health assistant, keeping
you updated about everything going on within your body. That will considerably shorten
treatment time and lower its intensity. As it is well known that the faster you detect the
disease, the easier it is to cure as shown in figure 4.8

Figure 4.8 Examples of AI

These are just a few examples of what the future of artificial intelligence and big data in
healthcare may look like. The physician of the future will only have to supervise the work done
by the AI algorithms and robots. And maybe in a much longer time, there will be no need for a
human physician? Just as it was in the Star Wars movies. Time will tell.
THE GENESIS OF AI IN MEDICINE AND HEALTHCARE

In 1959, Robert Ledley and Lee Lusted published a paper in Science, explaining the importance
of reasoning processes in medical diagnosis, and discussed the potential role of electronic
computers. This work is considered by many as the initiating paper that launched the field of
medical informatics. They used mathematical methods like Boolean algebra, Bayes theorem, and
symbolic logic to help identify the disease diagnosis. The next important development, in 1965,
was the DENDRAL project at Stanford University, by AI pioneer, Edward Feigenbaum, and
Nobel Prize winner, Joshua Lederberg. The rule-based and hypothesis-list approaches used in
the system helped identify unknown organic molecules by analysing their mass spectrometry
data.

AlphaGo playing against Lee Sedol.

Around this time, the National Institutes of Health in the US created the Stanford University
Medical Experimental – Artificial Intelligence in Medicine (SUMEX-AIM) laboratory. The idea
was to leverage the computing capabilities of the then newly introduced time-sharing computer,
PDP-10, and support the AIM research of various groups at Stanford, Rutgers

84
University, MIT, and the University of Pittsburgh. From these groups, four different AI systems
– INTERNIST 1, MYCIN, CASNET, and PIP – emerged in the 1970s.

 INTERNIST 1 – In 1972, Jack Myers, chairman of department of medicine at University

of Pittsburgh, and Harry Pople, a computer scientist with special interest in AI,
collaborated to develop a system for differential diagnosis in internal medicine. Called
Internist-1, the system contained a knowledge base of causal and taxonomic relationships
between clinical findings and diagnostic hypotheses, and used a powerful ranking
algorithm to reach diagnoses.
 MYCIN – In 1976, E.H. Shortliffe developed the MYCIN rule-based expert system for
infectious disease therapy assistance at the Stanford Medical School. In a comparative
test, case histories of ten patients suffering from meningitis were submitted to MYCIN
and to eight human physicians, for their diagnosis and recommendations. An independent
assessment found that MYCIN scored higher on both accuracy of diagnosis and
effectiveness of treatment.
 PIP – That same year, Steven Pauker and Anthony Gorry at MIT and Tufts New England
Medical Center, developed the Present Illness Program (PIP) system, an early diagnostic
tool in the evaluation of patients with oedema. PIP had four major components: patient
data, the knowledge repository of disease (representing a long- term memory), the
intersection of patient data and the knowledge repository (representing a short-term
memory), and a supervisor program to filter knowledge and act on patient input.
 CASNET – In 1978, Saul Amarel and Casimir Kulikowski of Rutgers University
developed CASNET, Causal Associational NETwork model for consultation in
glaucoma. It brought together ideas from two fields of computer science: statistical
pattern recognition (inference networks and probabilistic scoring of hypotheses) and
Artificial Intelligence (conceptual structure to represent disease processes, a model of
disease separated from decision-making strategies).

These went on to inspire the next generation of AI applications in the US. In the Indian context,
one of the earliest examples of AI in healthcare was a project by H.N. Mahabala and a team at
IIT Madras as part of India’s Knowledge-Based Computing Systems initiative in 1986. Eklavya
was a knowledge-based program designed to support a community health worker in dealing with
symptoms of illness in toddlers. Much later in the late 1990s, AI systems like IBM’s DeepBlue
and Watson emerged. In 2013, Watson was deployed at the Memorial Sloan Kettering Cancer
Centre. In 2020, Google DeepMind used AI to solve the ‘protein folding problem’, a grand
challenge that existed for over fifty years – and predict a protein’s three-dimensional structure
from its amino-acid sequence.

AI IN MEDICINE AND HEALTHCARE – IMPLICATIONS FOR THE FUTURE

 Let us go back to the two developments with which we started the article – AlphaFold
and WHO’s AI-in-health guidelines – and understand their implications for the future.

 What any given protein can do depends on its unique 3D structure. For example, antibody
proteins utilised by our immune systems are ‘Y-shaped’, and that shape helps them latch onto
viruses and bacteria. A tool like AlphaFold, with the power of AI techniques, might help
researchers predict the shape of a protein of interest for a rare disease, rapidly and
economically. A better understanding of protein folding and design will help in areas like

85
  efficient drug discovery – the use of 3D models can help understand why a certain drug
compound is an inhibitor or why certain proteins have more sites for drug delivery. The
availability of the AlphaFold database will provide opportunities for new research in areas
like structural biology and structural bioinformatics

4.5 ARTIFICIAL INTELLIGENCE IN HEALTHCARE

APPLICATIONS AND THREATS
 Remember Big Hero 6's beloved Baymax? The lead character’s personal pudgy robotic
healthcare companion was much loved and adored by the audience. We might not have
wondered back then but the fascinating machine had actually been powered with
Artificial Intelligence, programmed to scan a human body for any illnesses or injury
while also examining the environment, offering treatment, and even catering to the
emotional requirements of the patient.

 Although Baymax may appear as a complete fantasy creation from a children’s movie,
yet technology and robotics engineers throughout the globe are now working on making
healthcare AI become a practicality and reality from a fantasy.

 In line with this, over the years, the power of technology particularly AI has escalated by
leaps and bounds in various industries like AI in education, Sports such as AI in football,
AI in manufacturing, as well as AI in the healthcare industry.

AI IN HEALTHCARE

 At the initial stage, technology was merely used to automate the most routine and
monotonous tasks and cut down on the use of paper through digitization of health records
while also aiding in the easy flow of this information among insurance companies,
hospitals, and patients.

 While these tasks continue to be worked upon, Artificial Intelligence has expanded its
applications from being restricted to enhancing back-office productivity, to emerge as an
enabler to improve healthcare outcomes. Particularly in the present scenario of the
COVID era. While taking a toll on the personal health of the people, COVID has played a
huge part in putting the developing AI technologies into practice. The technology has
paved its way to developing new models, exploring new treatments, as well as in
developing the vaccine.

 From hospital care to clinical research, drug development to insurance, AI applications

are recasting the workings of the health sector to cut down on spending and enhance the
outcomes of the patient.

86
APPLICATIONS OF AI IN HEALTHCARE

From employing it to detect links between genetic codes, put to use surgical robots, or even for
maximizing hospital efficiency, AI has proven to be a boon for the healthcare industry

Support in Clinical Decisions

It's obviously imperative for health professionals to take every crucial piece of information into
consideration while diagnosing patients. As a result, this leads to sifting through various
complicated unstructured notes kept in medical records. If there's a mistake in keeping track of
even a single relevant fact, the life of a patient could be put at risk.

The assistance of Natural Language Processing (NLP) makes it more convenient for doctors to
narrow down all relevant information from patient reports.

Artificial Intelligence holds the ability to store and process large sets of data, which can provide
knowledge databases and facilitate examination and recommendation individually for each
patient, thus helping to enhance clinical decision support.

This technology can be relied upon by doctors for aid in detecting risk factors through
unstructured notes. An interesting example of this is IBM’s Watson has been employing AI for
predicting heart failure.

Enhance Primary Care and Triage through Chatbots

People have a tendency of booking appointments with their GP at the slightest threat or medical
issue, which could often turn out to be a false alarm or something which could be cured of self-
treatment.

Artificial Intelligence assists in enabling smooth flow and automation of primary care, allowing
doctors to stress over more crucial and dire cases.

87
Saving money on avoidable trips to the doctor, patients can benefit from medical
chatbots, which is an AI-powered service, incorporated with smart algorithms
that provide patients with instant answers to all their health-related queries and concerns while
also guiding them on how to deal with any potential problems.

These chatbots are 24/7 available and have the capacity to deal with multiple patients at the same
time.

Robotic Surgeries

AI and collaborative robots have revolutionized surgeries in terms of their speed, and depth while
making delicate incisions. Since robots don’t get tired, the issue of fatigue in the middle of
lengthy and crucial procedures is eliminated.

AI machines are capable of employing data from past operations to develop new surgical
methods. The preciseness of these machines reduces the possibility of tremors or any unintended
or accidental movements during the surgeries as shown in figure 4.9

Figure 4.9 Robotic Surgery

A few examples of Robots developed for surgeries are Vicarious Surgical which combines
virtual reality with AI-enabled robots so surgeons can perform minimally invasive operations as
well as Heartlander, a miniature mobile robot developed by the robotics department at Carnegie
Mellon University, which was developed to facilitate therapy on the heart.

88
Virtual nursing assistants

AI systems facilitate virtual nursing assistants that can perform a range of tasks from conversing
with patients to directing them to the best and effective care unit. These virtual nurses are
available 24/7 and can respond to queries as well as examine patients and provide instant
solutions.

Presently many AI-powered applications of virtual nursing assistants presently enable more
regular interactions between patients and care providers between office visits to avoid any
unnecessary hospital visits. The world’s first virtual nurse assistant Care Angel, can even
facilitate wellness checks through voice and AI.

Aiding in the accurate diagnosis

AI has the capacity to surpass human doctors and help them detect, predict, and diagnose diseases
more accurately and at a faster rate. Likewise, AI algorithms have proved to be not only accurate
and precise at specialty-level diagnostics, but also cost-effective in terms of detecting diabetic
retinopathy.

For instance, PathAI is developing machine learning technology to aid pathologists in making
more accurate diagnoses. The company's current goals include reducing error in cancer diagnosis
and developing methods for individualized medical treatment.

Buoy Health is an AI-based symptom and cure checker that uses algorithms to diagnose and treat
illness. Here's how it works: a chatbot listens to a patient’s symptoms and health concerns, then
guides that patient to the correct care based on its diagnosis.

Minimizing the burden of EHR use

EHRs have played an integral role in the healthcare industry’s journey towards digitalization, yet
its switch has introduced a variety of issues in association with cognitive overload, endless
documentation, and user burnout.

The EHR developers have started making use of AI for creating more intuitive interfaces and
automating a couple of the routine processes that consume a great degree of the user’s time.

While voice recognition and dictation are helping in enhancing the clinical documentation
process, yet natural language processing (NLP) tools may not go as far. AI can also aid in

89
processing routine requests from the inbox, such as medication refills, and result in notifications.
It can also aid in prioritizing tasks that require the clinician’s attention, making it simpler for the
users to operate with their to-do lists.

THREATS OF ARTIFICIAL INTELLIGENCE IN HEALTHCARE

As per a report from the Brookings Institution, there are several risks associated with AI in
healthcare that need to be addressed. Below are a couple of the threats which had been identified
by the Institution’s report :

Errors and Injuries

 One of the biggest risks that AI in healthcare holds is that the AI system might at times
be wrong, for instance, if it suggests a wrong drug to a patient or makes an error in
locating a tumor in a radiology scan, which could result in the patient’s injury or dire
health-related consequences.

 AI errors are potentially different for at least two reasons. While errors can obviously take
place by human medical professionals as well yet what makes this crucial is that an
underlying error, an error in an AI system could lead to injuries for thousands of patients.

Data availability

 Yet another threat posed by AI systems is that training these systems requires massive
amounts of data from multiple sources which include pharmacy records, electronic health
records, insurance claims records, etc.

 Since the data is fragmented and patients often see different providers or switch
insurance companies the data gets complicated and less comprehensible as a result of
which the risk of error and the cost of data collection escalates as shown in figure 4.10

Figure 4.10Threats of AI in Healthcare

90
 Privacy concerns

 The collection of huge datasets and the exchange of data between health systems and AI
developers to enable AI systems leads to many patients believing that this could violate
their privacy, leading to the filing of lawsuits.

 Another area where the employment of AI systems raises this issue is that AI has the
capability of predicting private information about patients even if the patient has never
given the information.

 For instance, Parkinson’s disease could be detected by an AI system with the trembling
on a computer mouse even if the person hasn’t revealed the information to anyone else
which could be considered a violation of privacy by the patient.

Bias and inequality

 Since AI systems absorb and learn through the data with which they are trained, they can
also absorb the biases of the available data. For example, if the data incorporated in AI is
mainly collected in academic medical centers, the developing AI systems will have less
awareness about, and as a result, will treat less effectively, patients from populations that
do not typically frequent academic medical cent In the long run, the employment of AI
systems could lead to shifts in the medical profession. Particularly in areas like radiology
where most of the work gets automated.

 This raises the concern that a high degree of employment of AI might lead to a fall in
human knowledge and capacity over the years, making providers fail in detecting AI
errors as well as in the further development of medical knowledge.

TEXT / REFERENCE BOOKS

1. Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in Health Care
and Biomedicine, Springer-Verlag London 2014.
2. Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionals and
Policymakers. 2016.
3. Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and information
technology professionals. Lulu Press. 2014 Seventh edition.
4. Gaddi A, Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic library holding in the
Health Science Library

91
 SCHOOL OF ELECTRICAL AND ELECTRONICS
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

UNIT – V– eHEALTH-SECA4004

92
UNIT-VAPPLICATION DEVELOPMENT FOR eHEALTH
Introduction to Android, Creating Android Activities, Android User interface design, Access
Wi-fi and Bluetooth with mobile applications-Web based App for eHealth applications.

ANDROID

Android is an open source and Linux-based operating system for mobile devices such as smart
phones and tablet computers. Android was developed by the Open Handset Alliance, led by
Google, and other companies. This tutorial will teach you basic Android programming and will
also take you through some advance concepts related to Android application development.
5.1 ANDROID - OVERVIEW
 Android is an open source and Linux-based Operating System for mobile devices such as
smartphones and tablet computers. Android was developed by the Open Handset Alliance,
led by Google, and other companies.
 Android offers a unified approach to application development for mobile devices which
means developers need only develop for Android, and their applications should be able to
run on different devices powered by Android.
 The first beta version of the Android Software Development Kit (SDK) was released by
Google in 2007 where as the first commercial version, Android 1.0, was released in
September 2008.
 On June 27, 2012, at the Google I/O conference, Google announced the next Android
version, 4.1 Jelly Bean. Jelly Bean is an incremental update, with the primary aim of
improving the user interface, both in terms of functionality and performance.
 The source code for Android is available under free and open source software licenses.
Google publishes most of the code under the Apache License version 2.0 and the rest, Linux
kernel changes, under the GNU General Public License version 2 as shown in Figure 5.1.

93
 Figure 5.1 Android Features

Features of Android

Android is a powerful operating system competing with Apple 4GS and supports great features.
Few of them are listed below −

S Feature & Description

r
.
N
o
.
1
Beautiful UI
Android OS basic screen provides a beautiful and
intuitiveuser interface.

2
Connectivity
GSM/EDGE, IDEN, CDMA, EV-DO, UMTS,
Bluetooth, Wi- Fi, LTE, NFC and WiMAX.

3
Storage
SQLite, a lightweight relational database, is used for
datastorage purposes.

94
4
Media support
H.263, H.264, MPEG-4 SP, AMR, AMR-WB, AAC,
HE-AAC, AAC 5.1, MP3, MIDI, Ogg Vorbis, WAV,

GIF, and BMP.

5
Messaging
SMS and MMS

6
Web browser
Based on the open-source WebKit layout engine,
coupled with Chrome's V8 JavaScript engine
supporting HTML5 and CSS3.

7
Multi-touch
Android has native support for multi-touch which
was initially made available in handsets such as the
HTC Hero.
8
Multi-tasking
User can jump from one task to another and same
time variousapplication can run simultaneously.

9
Resizable widgets
Widgets are resizable, so users can expand them to
show morecontent or shrink them to save space.

1
Multi-Language
0
Supports single direction and bi-directional text.

1
GCM
1
Google Cloud Messaging (GCM) is a service that
lets developers send short message data to their
users on Android devices, without needing a
proprietary sync solution.
1
Wi-Fi Direct
2
A technology that lets apps discover and pair
directly, over a high-bandwidth peer-to-peer
connection.

95
 1
Android Beam
3
A popular NFC-based technology that lets users
instantly share, just by touching two NFC-enabled
phones together.
JPEG, PNG,

ANDROID APPLICATIONS

 Android applications are usually developed in the Java language using the Android
SoftwareDevelopment Kit.
 Once developed, Android applications can be packaged easily and sold out either through
a store such as Google Play, SlideME, Opera Mobile Store, Mobango, F-droid
and the Amazon Appstore.
 Android powers hundreds of millions of mobile devices in more than 190 countries
around the world. It's the largest installed base of any mobile platform and growing fast.
Every day more than 1 million new Android devices are activated worldwide.
 This tutorial has been written with an aim to teach you how to develop and package
Android application. We will start from environment setup for Android application
programming andthen drill down to look into various aspects of Android applications.

CATEGORIES OF ANDROID APPLICATIONS

History of Android

The code names of android ranges from A to N currently, such as Aestro, Blender, Cupcake,
Donut, Eclair, Froyo, Gingerbread, Honeycomb, Ice Cream Sandwitch, Jelly Bean, KitKat,
Lollipop and Marshmallow. Let's understand the android history in a sequence as shown in
Figure 5.2.

96
 Figure 5.2 History of Android

ANDROID - ENVIRONMENT SETUP

You will be glad to know that you can start your Android application development on either of the
following operating systems
 Microsoft Windows XP or later version.
 Mac OS X 10.5.8 or later version with Intel chip.
 Linux including GNU C Library 2.7 or later.
Second point is that all the required tools to develop Android applications are freely available and
can be downloaded from the Web. Following is the list of software's you will need before you start
your Android application programming.
 Java JDK5 or later version
 Android Studio
Here last two components are optional and if you are working on Windows machine then these
components make your life easy while doing Java based application development. So let us have a
look how to proceed to set required environment.

SET-UP JAVA DEVELOPMENT KIT (JDK)

You can download the latest version of Java JDK from Oracle's Java site − Java SE Downloads.
You will find instructions for installing JDK in downloaded files, follow the given instructions to
install and configure the setup. Finally set PATH and JAVA_HOME environment variables to refer
to the directory that contains java and javac, typically java_install_dir/bin and java_install_dir
respectively.
97
If you are running Windows and installed the JDK in C:\jdk1.8.0_102, you would have to put
the following line in your C:\autoexec.bat file.
set PATH=C:\jdk1.8.0_102\bin;%PATH% set
JAVA_HOME=C:\jdk1.8.0_102
Alternatively, you could also right-click on My Computer, select Properties, then Advanced, then
Environment Variables. Then, you would update the PATH value and press the OK button.
On Linux, if the SDK is installed in /usr/local/jdk1.8.0_102 and you use the C shell, youwould
put the following code into your .cshrc file.
setenv PATH /usr/local/jdk1.8.0_102/bin:$PATH
setenv JAVA_HOME /usr/local/jdk1.8.0_102
Alternatively, if you use Android studio, then it will know automatically where you have
installed your Java.

ANDROID IDES

There are so many sophisticated Technologies are available to develop android applications, the
familiar technologies, which are predominantly using tools as follows
 Android Studio
 Eclipse IDE(Deprecated)
5.2 ANDROID - ARCHITECTURE

Android operating system is a stack of software components which is roughly divided into five
sections and four main layers as shown below in the architecture diagram as shown in figure
5.3.

98
 Figure 5.3 Android Architecture

LINUX KERNEL

At the bottom of the layers is Linux - Linux 3.6 with approximately 115 patches. This provides a
level of abstraction between the device hardware and it contains all the essential hardware drivers
like camera, keypad, display etc. Also, the kernel handles all the things that Linux is really good at
such as networking and a vast array of device drivers, which take the pain out of interfacing to
peripheral hardware.

LIBRARIES

On top of Linux kernel there is a set of libraries including open-source Web browser engine WebKit,
well known library libc, SQLite database which is a useful repository for storage and sharing of
application data, libraries to play and record audio and video, SSL libraries responsible for Internet
security etc.

ANDROID LIBRARIES

This category encompasses those Java-based libraries that are specific to Android development.
Examples of libraries in this category include the application framework libraries in addition to
those that facilitate user interface building, graphics drawing and database access. A summary of
some key core Android libraries available to the Android developer is as follows −
 android.app − Provides access to the application model and is the cornerstone of all
Android applications.

99
  android.content − Facilitates content access, publishing and messaging betweenapplications
and application components.
 android.database − Used to access data published by content providers and includes SQLite
database management classes.
 android.opengl − A Java interface to the OpenGL ES 3D graphics rendering API.
 android.os − Provides applications with access to standard operating system services
including messages, system services and inter-process communication.
 android.text − Used to render and manipulate text on a device display.
 android.view − The fundamental building blocks of application user interfaces.
 android.widget − A rich collection of pre-built user interface components such as buttons,
labels, list views, layout managers, radio buttons etc.
 android.webkit − A set of classes intended to allow web-browsing capabilities to be built
into applications.
Having covered the Java-based core libraries in the Android runtime, it is now time to turn our
attention to the C/C++ based libraries contained in this layer of the Android software stack.

ANDROID RUNTIME

 This is the third section of the architecture and available on the second layer from the bottom.
This section provides a key component called Dalvik Virtual Machine which is a kind of
Java Virtual Machine specially designed and optimized for Android.
 The Dalvik VM makes use of Linux core features like memory management and multi-
threading, which is intrinsic in the Java language. The Dalvik VM enables every Android
application to run in its own process, with its own instance of the Dalvik virtual machine.
 The Android runtime also provides a set of core libraries which enable Android application
developers to write Android applications using standard Java programming language.

APPLICATION FRAMEWORK

The Application Framework layer provides many higher-level services to applications in the form of
Java classes. Application developers are allowed to make use of these services in their applications.
The Android framework includes the following key services −
 Activity Manager − Controls all aspects of the application lifecycle and activity
stack.
 Content Providers − Allows applications to publish and share data with other
applications.
 Resource Manager − Provides access to non-code embedded resources such as strings,
color settings and user interface layouts.
 Notifications Manager − Allows applications to display alerts and notifications to the
user.

100
  View System − An extensible set of views used to create application user interfaces.

ANDROID - APPLICATION COMPONENTS

Application components are the essential building blocks of an Android application. These
components are loosely coupled by the application manifest file AndroidManifest.xml that
describes each component of the application and how they interact.
There are following four main components that can be used within an Android application −

S Components & Description

r
.
N
o

1 Activities
They dictate the UI and handle the user interaction to
the smart phone screen.

Services
2 They handle background processing associated with
anapplication.

Broadcast Receivers
3 They handle communication between

4 Content Providers
They handle data and database management issues.

ACTIVITIES

An activity represents a single screen with a user interface,in-short Activity performs actions on
the screen. For example, an email application might have one activity that shows a list of new
emails, another activity to compose an email, and another activity for reading emails. If an
application has more than one activity, then one of them should be marked as the activity that is
presented when the application is launched.
An activity is implemented as a subclass of Activity class as follows −
public class MainActivity extends Activity {
}

101
SERVICES

A service is a component that runs in the background to perform long-running operations. For
example, a service might play music in the background while the user is in a different
application, or it might fetch data over the network without blocking user interaction with an
activity.
A service is implemented as a subclass of Service class as follows −
public class MyService extends Service {
}

BROADCAST RECEIVERS

Broadcast Receivers simply respond to broadcast messages from other applications or from the
system. For example, applications can also initiate broadcasts to let other applications know that
some data has been downloaded to the device and is available for them to use, so this is
broadcast receiver who will intercept this communication and will initiate appropriate action.
A broadcast receiver is implemented as a subclass of BroadcastReceiver class and each
message is broadcaster as an Intent object.
public class MyReceiver extends BroadcastReceiver {
public void onReceive(context,intent){}
}

CONTENT PROVIDERS

A content provider component supplies data from one application to others on request. Such
requests are handled by the methods of the ContentResolver class. The data may be stored in the
file system, the database or somewhere else entirely.
A content provider is implemented as a subclass of ContentProvider class and must implement
a standard set of APIs that enable other applications to perform transactions.
public class MyContentProvider extends ContentProvider {
public void onCreate(){}
}

ADDITIONAL COMPONENTS

There are additional components which will be used in the construction of above mentioned
entities, their logic, and wiring between them. These components are

102
 S Components & Description
.
N
o
1 Fragments

Represents a portion of user interface in an Activity.

Views
2 UI elements that are drawn on-screen including
buttons, lists forms etc.

Layouts
3 View hierarchies that control screen format and
appearance ofthe views.

4 Intents
Messages wiring components together.

Resources
5 External elements, such as strings, constants and
drawablepictures.

6 Manifest
Configuration file for the application.

ANDROID - HELLO WORLD EXAMPLE

 Let us start actual programming with Android Framework. Before you start writing your
first example using Android SDK, you have to make sure that you have set-up your Android
development environment properly as explained in Android - Environment Set-up tutorial. I
also assume that you have a little bit working knowledge with Android studio.
 So let us proceed to write a simple Android Application which will print "Hello World!".
Create Android Application
 The first step is to create a simple Android Application using Android studio. When you
click on Android studio icon, it will show screen as shown below

103
 Figure 5.4 Android new studio

 You can start your application development by calling start a new android studio project
as shown in figure 5.4. in a new installation frame should ask Application name, package
information and location of the project as shown in figure 5.5

Figure 5.5 Android project

104
 Figure 5.6 Android target devices

 After entered application name, it going to be called select the form factors your
application runs on, here need to specify Minimum SDK, in our tutorial, I have declared
as API23: Android 6.0(Mashmallow) – as shown in figure 5.6
 The next level of installation should contain selecting the activity to mobile, it
specifiesdefault layout for Applications as shown in figure 5.7

Figure 5.7 Adding an activity

 At the final stage it going to be open development tool to write the application code as shown
in figure 5.8

105
 Figure 5.8Anatomy of Android Application

Before you run your app, you should be aware of a few directories and files in the Android
project

106
107
Following section will give a brief overview of the important application files. The Main Activity
File
 The main activity code is a Java file MainActivity.java. This is the actual application file
which ultimately gets converted to a Dalvik executable and runs your application. Following
is the default code generated by the application wizard for Hello World! application −
 Here, R.layout.activity_main refers to the activity_main.xml file located in
the res/layout folder. The onCreate() method is one of many methods that are figured when
an activity is loaded.

THE MANIFEST FILE

 Whatever component you develop as a part of your application, you must declare all its
components in a manifest.xml which resides at the root of the application project directory.
This file works as an interface between Android OS and your application, so if you do not
declare your component in this file, then it will not be considered by the OS. For example, a
default manifest file will look like as following file −
 Here <application>...</application> tags enclosed the components related to the application.
Attribute android:icon will point to the application icon available under res/drawable-hdpi.
The application uses the image named ic_launcher.png located in the drawable folders
 The <activity> tag is used to specify an activity and android:name attribute specifies the
fully qualified class name of the Activity subclass and the android:label attributes specifies a
string to use as the label for the activity. You can specify multiple activities using <activity>
tags.
 The action for the intent filter is named android.intent.action.MAIN to indicate that this
activity serves as the entry point for the application. The category for the intent-filter is
named android.intent.category.LAUNCHER to indicate that the application can be launch
from the device's launcher icon.
 The @string refers to the strings.xml file explained below. Hence, @string/app_name
refers to the app_name string defined in the strings.xml file, which is "HelloWorld".
Similar way, other strings get populated in the application.
Following is the list of tags which you will use in your manifest file to specify different Android
application components −
 <activity>elements for activities
 <service> elements for services
 <receiver> elements for broadcast receivers
 <provider> elements for content providers
The STRINGS FILE
The strings.xml file is located in the res/values folder and it contains all the text that your
application uses. For example, the names of buttons, labels, default text, and similar types of strings
go into this file. This file is responsible for their textual content. For example, a default strings file
will look like as following file −

108
THE LAYOUT FILE

 The activity_main.xml is a layout file available in res/layout directory, that is referenced by

your application when building its interface. You will modify this file very frequently to
change the layout of your application. For your "Hello World!" application, this file will
have following content related to default layout −
 This is an example of simple RelativeLayout which we will study in a separate chapter.
The TextView is an Android control used to build the GUI and it have various attributes
like android:layout_width, android:layout_height etc which are being used to set its width
and height etc.. The @string refers to the strings.xml file located in the res/values folder.
Hence, @string/hello_world refers to the hello string defined in the strings.xml file, which is
"Hello World!".

RUNNING THE APPLICATION

 Let's try to run our Hello World! application we just created. I assume you had created
your AVD while doing environment set-up. To run the app from Android studio, open one
of your project's activity files and click Run icon from the tool bar. Android studio
installs the app on your AVD and starts it and if everything is fine with your set-up and
application, it will display following Emulator window

 Congratulations!!! you have developed your first Android Application and now just keep
following rest of the tutorial step by step to become a great Android Developer. All the very
best.

ANDROID RESOURCES ORGANIZING & ACCESSING

 There are many more items which you use to build a good Android application. Apart from
coding for the application, you take care of various other resources like static content that
your code uses, such as bitmaps, colors, layout definitions, user interface strings, animation
instructions, and more. These resources are always maintained separately in various sub-
directories under res/ directory of the project.
 This tutorial will explain you how you can organize your application resources, specify
alternative resources and access them in your applications.
 Organize resource in Android Studio

ALTERNATIVE RESOURCES
 Your application should provide alternative resources to support specific device
configurations.
 For example, you should include alternative drawable resources ( i.e.images
) for different screen resolution and alternative string resources for different languages. At
runtime, Android detects the current device configuration and loads the appropriate
resources for your application.
To specify configuration-specific alternatives for a set of resources, follow the following steps −
 Create a new directory in res/ named in the form <resources_name>-
109
  <config_qualifier>. Here resources_name will be any of the resources mentioned in
the above table, like layout, drawable etc. The qualifier will specify an individual
configuration for which these resources are to be used. You can check official
documentation for a complete list of qualifiers for different type of resources.
 Save the respective alternative resources in this new directory. The resource files must
be named exactly the same as the default resource files as shown in the below example,
but these files will have content specific to the alternative. For example though image file
name will be same but for high resolution screen, its resolution will be high.
ACCESSING RESOURCES
During your application development you will need to access defined resources either in your code,
or in your layout XML files. Following section explains how to access your resources in both the
scenarios −

ACCESSING RESOURCES IN CODE

 When your Android application is compiled, a R class gets generated, which contains
resource IDs for all the resources available in your res/ directory. You can use R class to
access that resource using sub-directory and resource name or directly resource ID.

 Example
 To access res/drawable/myimage.png and set an ImageView you will use following code −
 Here first line of the code make use of R.id.myimageview to get ImageView defined with
id myimageview in a Layout file. Second line of code makes use of R.drawable.myimage to
get an image with name myimage available in drawable sub-directory under /res.
 If you have worked with C, C++ or Java programming language then you must have seen
that your program starts from main() function. Very similar way, Android system initiates
its program with in an Activity starting with a call on onCreate() callback method. There is
a sequence of callback methods that start up an activity and a sequence of callback methods
that tear down an activity as shown in the below Activity life cycle diagram: (image
courtesy : android.com ) as shown in Figure 5.9.

110
 Figure 5.9 Activity life cycle diagram

The Activity class defines the following call backs i.e. events. You don't need to implement all
the callbacks methods. However, it's important that you understand each one and implement
those that ensure your app behaves the way users expect.

 An activity class loads all the UI component using the XML file available
in res/layout folder of the project. Following statement loads UI components
from res/layout/activity_main.xml file:
setContentView(R.layout.activity_main);

 An application can have one or more activities without any restrictions. Every activity you
define for your application must be declared in your AndroidManifest.xml file and the main
111
 activity for your app must be declared in the manifest with an <intent-filter> that includes
the MAIN action and LAUNCHER category as follows:
 If either the MAIN action or LAUNCHER category are not declared for one of your
activities, then your app icon will not appear in the Home screen's list of apps.
 Let's try to run our modified Hello World! application we just modified. I assume you had
created your AVD while doing environment setup. To run the app from Android studio,
open one of your project's activity files and click Run icon from the toolbar. Android
studio installs the app on your AVD and starts it and if everything is fine with your setupand
application, it will display Emulator window and you should see following log messages in
LogCat window in Android studio −
 Let us try to click lock screen button on the Android emulator and it will generate following
events messages in LogCat window in android studio:
 Let us again try to unlock your screen on the Android emulator and it will generate
following events messages in LogCat window in Android studio:
 Next, let us again try to click Back button on the Android emulator and it will generate
following events messages in LogCat window in Android studio and this completes the
Activity Life Cycle for an Android Application.

A service has life cycle callback methods that you can implement to monitor changes in the service's
state and you can perform work at the appropriate stage. The following diagram on the left shows
the life cycle when the service is created with startService() and the diagram on the right shows the
life cycle when the service is created with bindService(): (image courtesy : android.com as shown
in figure 5.10

Figure 5.10 Service life cycle

To create an service, you create a Java class that extends the Service base class or one of its existing
subclasses. The Service base class defines various callback methods and the most important are
112
given below. You don't need to implement all the callbacks methods. However, it's important that
you understand each one and implement those that ensure your app behaves the way users expect.
Lets try to run our modified Hello World! application we just modified. I assume you had created
your AVD while doing environment setup. To run the app from Android studio, open one of your
project's activity files and click Run icon from the tool bar. Android Studio installs the app on
your AVD and starts it and if everything is fine with your set-up as shown in figure 5.11

Figure 5.11 Examples of service

and application, it will display following Emulator window −

Now to start your service, let's click on Start Service button, this will start the service and as
per our programming in onStartCommand() method, a message Service Started will appear on
the bottom of the the simulator as follows as shown in figure 5.12

113
 Figure 5.12To stop the service,
you can click the Stop Service buttonAndroid - UI Layouts

 The basic building block for user interface is a View object which is created from the View
class and occupies a rectangular area on the screen and is responsible for drawing and event
handling. View is the base class for widgets, which are used to create interactive UI
components like buttons, text fields, etc.
 The ViewGroup is a subclass of View and provides invisible container that hold other
Views or other ViewGroups and define their layout properties.
 At third level we have different layouts which are subclasses of ViewGroup class and a
typical layout defines the visual structure for an Android user interface and can be created
either at run time using View/ViewGroup objects or you can declare your layout using
simple XML file main_layout.xml which is located in the res/layout folder of your project
as shown in figure 5.13

114
 Figure 5.13 Layout params

 This tutorial is more about creating your GUI based on layouts defined in XML file.
Alayout may contain any type of widgets such as buttons, labels, textboxes, and so on.

 Android Layout TypesThere are number of Layouts provided by Android which you will
use in almost all the Android applications to provide different view, look and feel.

VIEW IDENTIFICATION

Following is a brief description of @ and + signs −

 The at-symbol (@) at the beginning of the string indicates that the XML parser should
parse and expand the rest of the ID string and identify it as an ID resource.
 The plus-symbol (+) means that this is a new resource name that must be created and
added to our resources. To create an instance of the view object and capture it from the
layout, use the following −

ANDROID - UI CONTROLS

115
 Figure 5.14 UI Elements

A View is an object that draws something on the screen that the user can interact with anda
ViewGroup is an object that holds other View (and ViewGroup) objects in order to define the
layout of the user interface.

CREATE UI CONTROLS

Input controls are the interactive components in your app's user interface. Android provides a wide
variety of controls you can use in your UI, such as buttons, text fields, seek bars, check box, zoom
buttons, toggle buttons, and many more

There are following three concepts related to Android Event Management −

 Event Listeners − An event listener is an interface in the View class that contains a single
callback method. These methods will be called by the Android framework when the View to
which the listener has been registered is triggered by user interaction with the item in the UI.
 Event Listeners Registration − Event Registration is the process by which an Event
Handler gets registered with an Event Listener so that the handler is called when the Event
Listener fires the event.
 Event Handlers − When an event happens and we have registered an event listener for the
event, the event listener calls the Event Handlers, which is the method that actually handles
the event.

There are many more event listeners available as a part of View class like OnHoverListener,
OnDragListener etc which may be needed for your application. So I recommend to refer official
documentation for Android application development in case you are going to develop a
sophisticated apps.
EVENT LISTENERS REGISTRATION
Event Registration is the process by which an Event Handler gets registered with an Event Listener
so that the handler is called when the Event Listener fires the event. Though there are several tricky
ways to register your event listener for any event, but I'm going to list down only top 3 ways, out of
which you can use any of them based on the situation.
 Using an Anonymous Inner Class

116
  Activity class implements the Listener interface.
 Using Layout file activity_main.xml to specify event handler
directly.
Below section will provide you detailed examples on all the three scenarios −
 Touch Model
Users can interact with their devices by using hardware keys or buttons or touching the
screen.Touching the screen puts the device into touch mode. The user can then interact
with it by touching the on-screen virtual buttons, images, etc.You can check if the device
is in touch mode by calling the View class’s isInTouchMode() method.
 Focus
A view or widget is usually highlighted or displays a flashing cursor when it’s in focus.
This indicates that it’s ready to accept input from the user.
 isFocusable() − it returns true or false
 isFocusableInTouchMode() − checks to see if the view is focusable in touch mode. (A
view may be focusable when using a hardware key but not when the device is in touch
mode)

EVENT HANDLING EXAMPLES

 Event Listeners Registration Using an Anonymous Inner Class

 Here you will create an anonymous implementation of the listener and will be useful if
each class is applied to a single control only and you have advantage to pass arguments
to event handler. In this approach event handler methods can access private data of
Activity. No reference is needed to call to Activity.
 But if you applied the handler to more than one control, you would have to cut and paste
the code for the handler and if the code for the handler is long, it makes the code harder
to maintain.
 Following are the simple steps to show how we will make use of separate Listener class
to register and capture click event. Similar way you can implement your listener for any
other required event type.

S Description
t
e
p
1 You will use Android studio IDE to create an Android
application and name it as myapplication under
a package com.example.myapplication as explained in
the Hello World Example chapter.

2 Modify src/MainActivity.java file to add click event

listeners and handlers for the two buttons defined.

117
 3 Modify the detault content of
res/layout/activity_main.xml file to include Android UI
controls.
4 No need to declare default string constants.Android
studio takescare default constants.

5 Run the application to launch Android emulator and

verify theresult of the changes done in the aplication.

 Following is the content of the modified main activity

file src/com.example.myapplication/MainActivity.java. This file can include each of the
fundamental lifecycle methods.
 Let's try to run your myapplication application. I assume you had created your AVD while
doing environment setup. To run the app from Android Studio, open one of your project's
activity files and click Run icon from the toolbar. Android Studio installs the app on your
AVD and starts it and if everything is fine with your setup and application, it will display
following Emulator window

Now you try to click on two buttons, one by one and you will see that font of the Hello World text
will change, which happens because registered click event handler method is being called against
each click event.

DEFINING STYLES
 A style is defined in an XML resource that is separate from the XML that specifies the
layout. This XML file resides under res/values/ directory of your project and will
have <resources> as the root node which is mandatory for the style file. The name of the
XML file is arbitrary, but it must use the .xml extension.
 You can define multiple styles per file using <style> tag but each style will have its name
that uniquely identifies the style. Android style attributes are set using <item> tag as shown
below −
STYLE INHERITANCE
 Android supports style Inheritance in very much similar way as cascading style sheet in web
design. You can use this to inherit properties from an existing style and then define only the
properties that you want to change or add.
 Your color resource can then be applied to some theme attributes, such as the window
background and the primary text color, by adding <item> elements to your custom theme.
These attributes are defined in your styles.xml file. For example, to apply the custom color
to the window background, add the following two <item> elements to your custom theme,
defined in MyAndroidApp/res/values/styles.xml file −

 A nine-patch drawable is a special kind of image which can be scaled in width and height
while maintaining its visual integrity. Nine-patches are the most common way to specify the
appearance of Android buttons, though any drawable type can be us.

118
STEPS TO CREATE NINE-PATCH BUTTONS

 Save this bitmap as /res/drawable/my_nine_patch.9.png

 Define a new style
 Apply the new button style to the buttonStyle attribute of your custom theme
 Android Themes
 Hope you understood the concept of Style, so now let's try to understand what is a Theme.
A theme is nothing but an Android style applied to an entire Activity or application, rather
than an individual View.
 Thus, when a style is applied as a theme, every View in the Activity or application will
apply each style property that it supports. For example, you can apply the
same CustomFontStyle style as a theme for an Activity and then all text inside
that Activity will have green monospace font.
 To set a theme for all the activities of your application, open the AndroidManifest.xml file
and edit the <application> tag to include the android:theme attribute with the style name.
For example −
 <application android:theme="@style/CustomFontStyle">
 But if you want a theme applied to just one Activity in your application, then add the
android:theme attribute to the <activity> tag only. For example −
 <activity android:theme="@style/CustomFontStyle">
 There are number of default themes defined by Android which you can use directly or
inherit them using parent attribute as follows −
 To understand the concept related to Android Theme, you can check Theme Demo Example.
 Styling the colour palette
 The layout design can implementable based on them based colours, for example as
following design is designed based on them colour(blue)

The Android platform provides a large collection of styles and themes that you can use in your
applications. You can find a reference of all available styles in the R.style class. To use the styles
listed here, replace all underscores in the style name with a period. For example, you can apply the
Theme_NoTitleBar theme with "@android:style/Theme.NoTitleBar". You can see the following
source code for Android styles and themes −

Android offers a great list of pre-built widgets like Button, TextView, EditText, ListView,
CheckBox, RadioButton, Gallery, Spinner, AutoCompleteTextView etc. which you can use directly
in your Android application development, but there may be a situation when you are not satisfied
with existing functionality of any of the available widgets. Android provides you with means of
creating your own custom components which you can customized to suit your needs.
If you only need to make small adjustments to an existing widget or layout, you can simply subclass
the widget or layout and override its methods which will give you precise control over the
appearance and function of a screen element.
This tutorial explains you how to create custom Views and use them in your application using
119
simple and easy steps as shown figure 5.15.

Figure 5.15 Example of Custom Components in Custom View hierarchyCreating a

Simple Custom Component
S Description
t
e
p
1 You will use Android studio IDE to create an
Androidapplication and name
it as myapplication under a
package
com.example.tutorialspoint7.myapplication as
explained in the Hello World Example chapter.
2 Create an XML res/values/attrs.xml file to define
newattributes along with their data type.

3 Create src/mainactivity.java file and add the code

to define your custom component

120
 4 Modify res/layout/activity_main.xml file and add
the code to create Colour compound view instance
along with few default attributes and new
attributes.
5 Run the application to launch Android emulator
and verify the result of the changes done in the
application.
5.3 ACCESS WI-FI ON AN ANDROID PHONE

 Making Wi-Fi work on your Android phone requires two steps. First, you must activate
Wi-Fi by turning on the phone’s wireless radio. The second step is connecting to a
specific wireless network.
 Wi-Fi stands for wireless fidelity. It’s brought to you by the numbers 802.11 and the
letters B, N, and G.
Activating Wi-Fi
Follow these steps to activate Wi-Fi on your Android phone:
 At the Home screen, touch the Apps icon. Open the Settings app.
 Ensure that the Wi-Fi master control icon is on.
 If not, slide the master control from Off to On to activate the phone’s Wi-Fi radio.
 If you’ve already configured your phone to connect to an available wireless network, it’s
connected automatically. Otherwise, you have to connect to an available network, which is
covered in the next section.
 To turn off Wi-Fi, repeat the steps in this section, but in Step 3 slide the master control icon
from On to Off. Turning off Wi-Fi disconnects your phone from any wireless networks.
 Some phones may come with a Power Control widget affixed to a Home screen. One of the
buttons on that widget is used to turn Wi-Fi on or off.

Using Wi-Fi to connect to the Internet doesn’t incur data usage charges.
 The Wi-Fi radio places an extra drain on the battery, but it’s truly negligible.
 If you want to save a modicum of juice, especially if you’re out and about and don’t plan to
be near a Wi-Fi access point for any length of time, turn off the Wi-Fi radio.
CONNECTING TO A WI-FI NETWORK
After activating the Wi-Fi radio on your Android phone, you can connect to an available wireless
network. Heed these steps:
Open the Settings app.
 It’s found in the apps drawer, but you’ll also find a shortcut in the quick actions drawer.
Choose Wi-Fi or Wireless & Networks.
 Don’t touch the Master Control icon, which turns the Wi-Fi radio on or off; touch theWi-
Fi text on the left side of the Settings app screen.

121
  You see a list of Wi-Fi networks. In the figure, the Imperial Wambooli network is

 currently connected as shown in figure 5.16

Figure 5.16 Choose a wireless network from the list.

 When no wireless networks are shown, you’re sort of out of luck regarding Wi-Fi access
from your current location.
 If prompted, type the network password.
 Putting a check mark in the box by the Show Password option makes it easier to type a
long, complex network password.
 Touch the Connect button.
 You should be immediately connected to the network. If not, try the password again.
 When the phone is connected, you see the Wi-Fi status icon atop the touchscreen,
looking similar to the icon shown. This icon indicates that the phone’s Wi-Fi is on —
connected and communicating with a Wi-Fi network.

 Some wireless networks don’t broadcast their names, which adds security but also makes
accessing them more difficult. In these cases, touch the Add icon to manually add the
network. The command might be titled Add Network.
You need to type the network name, or SSID, and specify the type of security. You also need the
password, if one is used. You can obtain this information from the girl with the pink hair and
pierced lip who sold you coffee or from whoever is in charge of the wireless network at your
location.
122
  Not every wireless network has a password. They should!
 Some public networks are open to anyone, but you have to use the web browser app to
get on the web and find a login page that lets you access the network. Simply browse to
any page on the Internet, and the login page shows up.
 The phone automatically remembers any Wi-Fi network it’s connected to as well as its
network password. An example is the AS_BOARD_ROOM network, shown.
 To disconnect from a Wi-Fi network, simply turn off Wi-Fi.
 Unlike the mobile network, a Wi-Fi network’s broadcast signal goes only so far. Use Wi-
Fi when you plan to remain in one location for a while. If you wander too far away, your
phone loses the signal and is disconnected.
CONNECTING VIA WPS
 Many Wi-Fi routers feature WPS, which stands for Wi-Fi Protected Setup. It’s a network
authorization system that’s really simple and quite secure. If the wireless router features
WPS, you can use it to quickly connect your phone to the network.
 To make the WPS connection, touch the WPS connection button on the router. The
button is labeled WPS or sports the WPS icon. On your phone, visit the Wi-Fi screen in
the settings app. Touch the WPS icon to connect to the network.

 If the WPS router requires a PIN (Personal Identification Number), touch the Action
Overflow icon on the Wi-Fi settings screen and choose the WPS Pin Entry item.

5.5 BLUETOOTH

The Android platform includes support for the Bluetooth network stack, which allows a device to
wirelessly exchange data with other Bluetooth devices. The app framework provides access to the
Bluetooth functionality through Bluetooth APIs. These APIs let apps connect to other Bluetooth
devices, enabling point-to-point and multipoint wireless features.
Using the Bluetooth APIs, an app can perform the following:Scan for other Bluetooth devices.
Query the local Bluetooth adapter for paired Bluetooth devices.

123
  Establish RFCOMM channels.
 Connect to other devices through service discovery.
 Transfer data to and from other devices.
 Manage multiple connections.
 This topic focuses on Classic Bluetooth. Classic Bluetooth is the right choice for more
battery-intensive operations, which include streaming and communicating between
devices. For Bluetooth devices with low power requirements, consider using Bluetooth
Low Energy connections.
 This documentation describes different Bluetooth profiles and explains how to use the
Bluetooth APIs to accomplish the four major tasks necessary to communicate using
Bluetooth:
 Setting up Bluetooth.
 Finding devices that are either paired or available in the local area.
Connecting devices.
 Transferring data between devices.
 For a demonstration of using the Bluetooth APIs, see the Bluetooth Chat sample app.

THE BASICS

For Bluetooth-enabled devices to transmit data between each other, they must first form a channel of
communication using a pairing process. One device, a discoverable device, makes itself available
for incoming connection requests. Another device finds the discoverable device using a service
discovery process. After the discoverable device accepts the pairing request, the two devices
complete a bonding process in which they exchange security keys. The devices cache these keys for
later use. After the pairing and bonding processes are complete, the two devices exchange
information. When the session is complete, the device that initiated the pairing request releases the
channel that had linked it to the discoverable device. The two devices remain bonded, however, so
they can reconnect automatically during a future session as long as they're in range of each other
and neither device has removed the bond.
 Use of the Bluetooth APIs requires declaring several permissions in your manifest file. Once
your app has permission to use Bluetooth, your app needs to access the
BluetoothAdapter and determine if Bluetooth is available on the device. If Bluetooth is
available,
There are three steps to make a connection:
 Find nearby Bluetooth devices, either devices that are already paired or new ones. Connect to
a Bluetooth device.

 Transfer data with the connected device.

 Certain devices use a specific Bluetooth profile that declares the data it provides.

124
KEY CLASSES AND INTERFACES

 All of the Bluetooth APIs are available in the android.bluetooth package.

 The following are the classes and interfaces you need in order to create Bluetooth
connections:BluetoothAdapter
 Represents the local Bluetooth adapter (Bluetooth radio).
 The BluetoothAdapter is the entry-point for all Bluetooth interaction.
 Using this, you can discover other Bluetooth devices, query a list of bonded (paired)
devices, instantiate a BluetoothDevice using a known MAC address, and create a
BluetoothServerSocket to listen for communications from other devices.
BLUE TOOTH DEVICE
REPRESENTS A REMote Bluetooth device. Use this to request a connection with a remote device
through a BluetoothSocket or query information about the device such as its name, address, class,
and bonding state.
BLUE TOOTH SOCKET
Represents the interface for a Bluetooth socket (similar to a TCP Socket). This is the connection
point that allows an app to exchange data with another Bluetooth device using InputStream and
OutputStream.
BLUE TOOTH SERVER SOCKET
Represents an open server socket that listens for incoming requests (similar to a TCP
ServerSocket). In order to connect two devices, one device must open a server socket with this
class. When a remote Bluetooth device makes a connection request to this device, the device
accepts the connection and then returns a connected BluetoothSocket.
BLUE TOOTH CLASS
Describes the general characteristics and capabilities of a Bluetooth device. This is a read-only set of
properties that defines the device's classes and services. Although this information provides a useful
hint regarding a device's type, the attributes of this class don't necessarily describe all Bluetooth
profiles and services that the device supports.
BLUE TOOTH PROFILE
An interface that represents a Bluetooth profile. A Bluetooth profile is a wireless interface
specification for Bluetooth-based communication between devices. An example is the Hands-Free
profile. For more discussion of profiles, see Bluetooth profiles.
BLUE TOOTH HEADSET
Provides support for Bluetooth headsets to be used with mobile phones. This includes both the
Bluetooth Headset profile and the Hands-Free (v1.5) profile.
BLUETOOTH A2DP
Defines how high-quality audio can be streamed from one device to another over a Bluetooth
connection using the Advanced Audio Distribution Profile (A2DP).
BLUETOOTH HEALTH
Represents a Health Device Profile proxy that controls the Bluetooth service.
125
BLUE TOOTH HEALTH CALLBACK
An abstract class that you use to implement BluetoothHealth callbacks. You must extend this class
and implement the callback methods to receive updates about changes in the app’s registration state
and Bluetooth channel state.
BLUE TOOTH HEALTHAPP CONFIGURATION
Represents an app configuration that the Bluetooth Health third-party app registers to communicate
with a remote Bluetooth health device.
BLUE TOOTH PROFILE.SERVICELISTENER
An interface that notifies BluetoothProfile interprocess communication (IPC) clients when they
have been connected to or disconnected from the internal service that runs a particular profile.

ANDROID - BLUETOOTH

 Among many ways, Bluetooth is a way to send or receive data between two different
devices. Android platform includes support for the Bluetooth framework that allows a device
to wirelessly exchange data with other Bluetooth devices.
 Android provides Bluetooth API to perform these different operations. Scan for other
Bluetooth devices
 Get a list of paired devices
Connect to other devices through service discovery
Android provides BluetoothAdapter class to communicate with Bluetooth. Create an object of
this calling by calling the static method getDefaultAdapter(). Its syntax is given below.
Apart from this constant, there are other constants provided the API , that supports different
tasks. They are listed below.

S Constant & description

r
.
N
o

ACTION_REQUEST_DISCOVERABLE
1
This constant is used for turn on discovering
ofBluetooth

ACTION_STATE_CHANGED
2 This constant will notify that Bluetooth state
has beenchanged

3 ACTION_FOUND

126
 This constant is used for receiving information
about each device that is discovered

Apart form the parried Devices , there are other methods in the API that gives more control
over Blueetooth. They are listed below.

S Method & description

r
.
N
o

1 enable()
This method enables the adapter if not enabled

2 isEnabled()
This method returns true if adapter is enabled

3 disable()
This method disables the adapter

4 getName()
This method returns the name of the Bluetooth
adapter

5 setName(String name)
This method changes the Bluetooth name

getState()
6 This method returns the current state of the
BluetoothAdapter.

startDiscovery()
7 This method starts the discovery process of the
Bluetooth for 120 seconds.

127
Example

This example provides demonstration of BluetoothAdapter class to manipulate Bluetoothand show

list of paired devices by the Bluetooth.
To experiment with this example , you need to run this on an actual device.

S Description
t
1e You will use Android studio to create an Android
p application a package
s com.example.sairamkrishna.myapplication.

2 Modify src/MainActivity.java file to add the code

3 Modify layout XML file

res/layout/activity_main.xml add any GUI
component if required.
4 Modify AndroidManifest.xml

5 Run the application and choose a running android

device and install the application on it and verify
the results.

128
5.5 STEPS OF HEALTHCARE MOBILE APP DEVELOPMENT SERVICES

 Step 1. Choose your technological partner among healthcare software development

companies
When choosing the best healthcare dev company, consider previous projects, client reviews,
and the company’s tech expertise.
 Step 2. Ask developers for a quote to create a healthcare app
Fill in the contact form to schedule a meeting with a business development manager to
clarify more details of your project.
 Step 3. Receive a rough estimate on medical app development
Based on the project's details, a business analyst, project manager, and solutions architect
will create a rough estimation for your project and send it to you.
 Step 4. Launch the inception phase with a team of medical app developers
When you agree on the initial estimation, healthcare app developers will clarify more
details on your project to create user stories, mockups, and wireframes.
 Step 5. Start the healthcare software development process
When you agree on all deliverables of the inception phase, the team will start building the
app iteration by iteration.

TYPES OF MOBILE HEALTH APPS

There are different types of apps for health aimed at various end-users, including medical
professionals, labs, and patients, which impact their features, some integrations, and the degree of
data security required.

PROFESSIONAL HEALTHCARE APP

Targeted at medical personnel, such apps include patient data, such as name, date of birth, insurance
number, address, and so on. Thus, when launching a professional healthcare development process,
you need to make a medical personal mobile app HIPAA compliant and pay extra attention to
private data encryption to avoid data breaches. mHealth apps for medical specialists include the
following types:

CLINICAL COMMUNICATION APPS

 Such applications are developed to improve clinical decision-making and communication

with clinical specialists in a particular hospital. They include messaging and voice chat, file
sharing, and electronic health record systems.
 One example of such an app is Halo, a communication, and collaboration platform for
clinical specialists, which includes the following features:
 Send physicians and nurses Lab and PACS results
 Integrate with EHR (electronic health records) to edit patient records in real-time Store files
on a cloud-based platform, Amazon Web Services

129
PATIENT COMMUNICATION APPS

 This type of app boosts customer satisfaction, loyalty, health outcomes, and provides
more transparency between patients and doctors.
 That is how the EASE mobile app works, offering users the following features: Invite
relatives to the network within the app to keep them informed about updates
 Include HIPAA compliant texts, photos, and videos that will self-destruct after 60seconds
 Send premade bulk messages to patients and their families to keep them informed
 Prohibit saving files, texts, or other documents from the app to the device to ensure
patient privacy and avoid data breaches

MEDICAL RECORD APPS

 Such apps simplify updating patient records, including blood pressure, medical visits,
examinations, prescriptions, and other information to keep track of a patient's progress.
 Medical Record is an app that belongs to this mHealth app category. In addition to the
features above, the app also includes:
 Prescription module allowing doctors to save medical info Appointment feature to schedule
an appointment with patients Recording videos or procedures instead of text messages
Searching patients by I.D.

RISK ASSESSMENT APPS

 Such apps are integrated with Electronic Health Records (EHR) and wearable devices, which
allows monitoring patients' health conditions in real-time, tracking heart rate, and identifying
patients at risk. To build a risk assessment mobile app, developers often use machine
learning for pattern recognition, as we did for our recent project, a skin cancer detection
neural network.
 An example of such an app is FHR 5-Tier(Forecast Health Risk and Predication), aimed at
obstetricians, midwives, and nurses who use electronic fetal monitoring (EFM) for patients
in labor. Let's look at its features:
 The app allows interpreting fetal heart rate (FHR) tracings to decide about further patient
treatment in real-time
 The five-color (green, blue, yellow, orange, and red) system is used in the app to allow
medical specialists to standardize the management of different fetal heart rate tracings.
 When the app finds a risk to a patient's health, it uses colors Yellow, Orange, or Red to
notify the doctor about the patient's state of urgency and provide a list with recommended
actions.

BARCODE SCANNING APPS

 Barcode scanning mobile apps in healthcare allow scanning a patient's electronic health
records and medication barcodes using a built-in camera in their mobile devices, avoiding
expensive barcode scanning devices.

130
  Epic Rover is one healthcare app that belongs to this category, empowered by Scandid
Barcode scanner SDK. Apart from scanning a patient's medications barcodes, develop a
healthcare mobile app with the following features:
 Integration with Epic electronic health records for better admission of medicines and
treatment
 Visualization of patient-related info and progress in the form of charts
 Build-in messenger to communicate with patients and other medical personnel And other
functions to make the doctors' work even more efficient.
MEDICATION DOSAGE APPS

 Such applications are used by physicians to calculate individualized doses of medicine based
on the patient's age, weight, and other personal info, avoiding laborious manual calculations,
spreadsheets, and sophisticated tools.
 One example is the DoseMeRx app for medical professionals. Let's find out more about its
features:
 Integration with EHR, where the doctor can leave notes on the patient's state, medications,
and dosage assigned
 Set up reminders so that patients can track their medication intake Build-in feature to predict
treatment outcomes
 Integrated dose optimization feature that leverages Bayesian dosing methods to guide dose
optimization, based on clinically validated pharmacokinetic drug models, patient
characteristics, drug concentrations, and genotype

HOSPITAL MOBILE APP DEVELOPMENT

Healthcare mobile apps for patients

The patient-oriented mobile app market includes two main categories: medical and wellness. Below,
we highlight every type of app from both of these groups, their examples, and essential features.

Doctor-on-demand or Telemedicine apps

 Even in a busy environment, patients can receive treatment and consultations from medical
specialists using telemedicine apps, without leaving their offices or homes. Such mobile
applications help patients to find a necessary medical specialist from a pool of doctors, book
an appointment, and attend it via video call and pay for the consultation via an integrated
payment gateway.
 One typical doctor-on-demand mobile app is EVisit that includes other features:
 Virtual waiting room with waiting time tracking where patients can prepare the information
required
 Two-way video connection so patients can see the doctors they communicate with
 Built-in messaging, EHR, search for medication, prescriptions, and other features to deliver
patients the medical experience of attending an offline appointment with a doctor.

131
Condition-based apps

 Such apps are popular among users with epilepsy, diabetes, cardiovascular disease, asthma,
allergies, and even depression. While some apps in this category are more sophisticated
versions of a digital diary with visual medication management, others
 use predictive analytics and machine learning to notify a user about a particular health
condition one should be aware of.
 Founded by Munroe-Meyer Institute, Seizure Tracker is a perfect example of apps that
allow users to log their seizures, and includes a bunch of other features:
 Video recording, so patients can describe their seizures, their triggers, and what happened
afterward
 Manual input of seizure info, so the user can specify their seizure type, time of day,
length of the seizure, and other related information
 Option to synchronize user profile with private Youtube channel to record info about
seizures and share it with relatives

Fitness apps

 Such apps help users keep fit by tracking their daily activity, weight, number of calories
burned, a list with workout programs, and integration with wearable devices. In our previous
article devoted to fitness app development, we described other features of such apps and
gave you a guide on how to develop one.
 MyFitnessPal is the most popular fitness mobile app, which includes:
 Diet tracking with recommendations on calorie consumption based on the user's age, weight,
sex
 User community where other users share their success stories about losing weight Calorie
counter to control the amount of food, water and coffee consumed

Diet and nutrition apps

 Diet and nutrition apps are another popular category in the mHealth market, targeted at users
who want to lose weight. The standard set of a diet app includes a comprehensive library
with food and nutrition, a calorie counter, a diary with meals, and a progress chart.
 Lose It! app belongs to this mobile app category and provides users with the following
features:
 Barcode scanner to receive information about product nutrients within seconds, and track
intake of carb, macro, and calorie
 Snap It allows users to log images of food taken on a mobile device
 Meal planning to customize the user's eating and track macro, carb, protein, and overall
calorie intake

132
Meditation apps

 Meditation mobile apps also belong to the mHealth market since they help users to maintain
their mental health with the help of guided meditations. As a rule, such apps include a library
with pre-recorded sessions of guided meditations, timer, gamification, and useful tips about
breathing exercises.
 Calm, the best-known meditation mobile app, valued at $1 billion, helps users reduce stress
and improve sleep. To achieve these goals, they use not only ancient methods of relaxation,
but also a scientific approach based on ongoing studies conducted by scientist from Arizona
State University, Ryerson University in Toronto, Massachusetts General Hospital, and
others.
 The main features of the Calm app are:
 Guided meditations for different purposes (relationships, breaking habits, happiness, etc.

 Mediations of different lengths for users with varying levels

 A library with podcasts, sleeping stories, relaxing music, breathing programs, and
masterclasses

Regulations to consider before starting a healthcare app development

 If you want to build a mobile medication app, things to consider are security regulations and
compliances across different countries that are mainly concerned with patient data safety.
Otherwise, if your app does not meet these regulations, no matter how good your app is, it
will be deleted from app marketplaces.
 The good thing is to build a weight loss, calorie counter, or meditation app, you do not need
to make it compliant.

TEXT / REFERENCE BOOKS

1. Shortliffe, Edward H and Cimino James J. Biomedical Informatics, Computer Applications in Health Care and
Biomedicine, Springer-Verlag London 2014.
2. Lavis, JN (ed). Ontario's Health System: Key Insights for Engaged Citizens, Professionals and
Policymakers. 2016.
3. Hoyt RE, Yoshihashi A, Bailey N. Health informatics: Practical guide for healthcare and information
technology professionals. Lulu Press. 2014 Seventh edition.
4. Gaddi A, Capello F, Manca M. eHealth, Care and Quality of Life. 2014 electronic library holding in the Health
Science Library

133