TECHNOLOGY LAB REPORT

Title:DATA ANALYTICS IN HEALTHCARE:CASE

STUDY ON OpenEyes

BY

M23MSA003- Aditi Rajoliya

M23MSA021- Aswin G Nath

M23MSA032- Eshan Save

M23MSA033- Gaurav Chaudhary

M23MSA040- Hemavarshini J

M23MSA049 – Loukik Rawal

Abstract:

Data analytics in healthcare involves collecting, processing, and analyzing healthcare data using
techniques like machine learning and real-time monitoring. It encompasses descriptive analytics
(identifying trends), predictive analytics (forecasting outcomes), and prescriptive analytics
(actionable insights). OpenEyes, an open-source Electronic Health Record system, demonstrates this
approach by managing patient records and appointments. It employs data analytics to track
operational metrics, improve decision-making, prevent problems, reduce waste, and enhance
efficiency. Overall, data analytics in healthcare enhances patient care, streamlines operations, and
informs critical decisions, with applications like OpenEyes exemplifying its transformative potential.
Introduction:

Data analytics has become a pivotal force in the healthcare industry, revolutionizing patient care and
organizational efficiency. This multidimensional approach involves the systematic collection,
processing, and analysis of healthcare data, utilizing advanced techniques such as machine learning,
statistical modeling, and real-time monitoring. Within this framework, several essential components
are at play.

Descriptive analytics enables the identification of historical trends and patterns, shedding light on
patient demographics, disease prevalence, and healthcare utilization. Predictive analytics leverages
statistical and AI techniques to forecast future events, from disease outbreaks to patient
readmissions and treatment outcomes. Prescriptive analytics goes a step further, translating data
analysis into actionable insights for treatment planning, resource allocation, and targeted
interventions.

Real-time monitoring is indispensable, especially in critical care settings, allowing for rapid
identification and response to changes in patient health. Identifying patterns in health data aids in
assessing risks and developing tailored solutions for specific populations, while enhancing
operational efficiency by streamlining administrative procedures, patient flow, and resource
allocation.

In this context, OpenEyes, an open-source Electronic Health Record system designed for
ophthalmology departments and eye clinics, serves as an illustrative example of data analytics
application. It streamlines patient record management, appointment scheduling, surgical procedures,
and compliance with healthcare standards. This paper delves into how OpenEyes harnesses data
analytics to optimize its operations and ultimately contributes to the advancement of healthcare
delivery and management.

DATA ANALYTICS IN HEALTHCARE

In order to get insights for enhancing patient care and operational efficiency, data analytics in
healthcare comprises gathering, processing, and analyzing healthcare data. It includes methods like
machine learning, statistical modeling, and real-time monitoring to accomplish:

❑ Descriptive analytics: you can find trends and patterns in patient demographics, illness
prevalence, and healthcare use by summarizing historical data.

❑ Predictive analytics: the use of statistical and AI techniques to predict future occurrences,
such as disease outbreaks, readmissions of patients, and treatment outcomes.

❑ Prescriptive analytics: Using data analysis to provide actionable insights for treatment
planning, resource allocation, and interventions.

❑ Real-time monitoring: Using data, especially in critical care situations, to quickly identify and
react to changes in patient health.

❑ Identifying Patterns: Analyzing data to identify patterns in health, evaluate risks, and
develop tailored solutions for certain populations.

❑ Operational Efficiency: Improving administrative procedures, patient flow, and resource

allocation using data-driven insights.
 ❑ Personalized medicine : Individualizing treatments and advice based on a patient's traits,
genetics, and preferences is known as.

OpenEyes
OpenEyes is an open-source EHR system specifically designed for ophthalmology departments and
eye clinics. It helps healthcare professionals manage patient records, appointments, surgeries, and
other aspects of eye care. OpenEyes aims to provide a cost-effective solution for eye care providers
while maintaining compliance with healthcare standards.

An EHR is an electronic system used and maintained by healthcare systems to collect and store
patients’ medical information.c EHRs are used across clinical care and healthcare administration to
capture a variety of medical information from individual patients over time, as well as to manage
clinical workflows. EHRs contain different types of patient-level variables, such as demographics,
diagnoses, problem lists, medications, vital signs, and laboratory data. According to the National
AcadUsing data-driven insights to improve administrative procedures, patient flow, and resource
allocationion, orders and results manageUsing data-driven insights to improve administrative
procedures, patient flow, and resource allocationrt, administrative proceses, and population health
reporting.2
In summary, registries are patient-centered, purpose-driven, and designed to derive information on
defined exposures and health outcome. In contrast, EHRs are visit-centered and transactional.
Despite these differences, EHRs capture a wealth of data that is relevant to patient registries. EHRs
also may assist in certain functions that a patient registry requires (e.g., data collection, data
cleaning, data storage), and a registry may augment the value of the information collected in an EHR
(e.g., comparative safety, effectiveness and value, population management, quality reporting)

• Patient table: This table stores information about each patient, such as their name, address,
date of birth, insurance information, and medical history.

• Encounter table: This table stores information about each patient's visit, such as the date and
time of the visit, the provider who saw the patient, the procedures and medications that
were administered, and the diagnosis

• Clinical Document table: This table stores the actual clinical documents for each patient, such
as progress notes, discharge summaries, and radiology reports.

• Provider table: This table stores information about each provider who is affiliated with the
healthcare organization, such as their name, license number, and specialty.

• Procedure table: This table stores information about each procedure that is performed at the
healthcare organization, such as the name of the procedure, the CPT code, and the
description.

• Medication table: This table stores information about each medication that is dispensed at
the healthcare organization, such as the name of the medication, the dosage, and the
frequency.

• Insurance table: This table stores information about each patient's insurance, such as the
name of the insurance company, the policy number, and the expiration date
 Use of Data analytics IN OpenEyes-
• Descriptive analytics: This technique is used to describe the data and identify trends. For
example, OpenEyes can be used to describe the demographics of patients, the types of
procedures that are performed, and the medications that are prescribed.

• Diagnostic analytics: This technique is used to identify patterns in the data that can be used
to diagnose problems. For example, OpenEyes can be used to identify patients who are at
risk for certain diseases or who are not responding to treatment.

• Predictive analytics: This technique is used to predict future events based on historical data.
For example, OpenEyes can be used to predict which patients are most likely to be
readmitted to the hospital or which patients are most likely to develop a certain disease.

• Prescriptive analytics: This technique is used to recommend actions that can be taken to
improve patient care. For example, OpenEyes can be used to recommend changes to
treatment plans or to identify patients who need additional care.

How OpenEyes Uses Data to Optimize Operations-

• Tracking operational metrics:

• OpenEyes tracks a variety of operational metrics, such as the number of patients seen per
day, the cost of supplies, and the number of staff hours worked. This data helps them to
identify areas where operations can be optimized. For example, if they see that the cost of
supplies is increasing, they can investigate the reasons for this and take steps to reduce costs.

• Making better decisions:

• OpenEyes uses data to make better decisions about resource allocation, scheduling, and
staffing. For example, they can use data to predict patient demand and allocate resources
accordingly. They can also use data to schedule appointments more efficiently and staff their
operations with the right number of people.

• Preventing problems:

• OpenEyes uses data to prevent problems before they happen. This includes identifying
potential risks and taking steps to mitigate them. For example, if they see that a particular
type of medication is causing adverse reactions, they can work to prevent patients from
being prescribed this medication.

• Identifying waste:

• OpenEyes uses data to identify waste in their operations. This includes identifying
unnecessary tests, procedures, and staff hours. For example, if they see that a particular test
is being ordered unnecessarily, they can work to reduce the number of times this test is
ordered.

• Improving efficiency:
 • OpenEyes uses data to improve the efficiency of their operations. This includes identifying
bottlenecks and streamlining processes. For example, if they see that there is a long wait
time to see a doctor, they can work to streamline the process so that patients can be seen
more quickly.

• Common data types of EHRs that can be integrated/interfaced with internal/external

registries

DATA TYPE EXAMPLE

Demographics age, sex/gender, race

Diagnoses diagnosis, severity, medical history

Problem List active diagnosis, resolved diagnosis

Family History familial disorders, risk factors

Allergies food and medication allergy, anaphylaxis

Immunization DTaP, HepB, IPV

Medications Prescriptions written

Procedures inpatient, outpatient

Lab Orders/Values CBC results, HbA1C levels

Vital Signs BMI (weight and height), blood pressure

Reports radiology, pathology and other reports

Utilization cost, hospitalization

Emerging Data Types

Biosample Data meta data about a biological sample

Genetic Information genome sequence data

DATA TYPE EXAMPLE

Social Data income level, education, employment status

Patient-Generated mHealth, patient communications

Community community specifications

Geo-spatial neighborhood built environment

Surveys HRA, PHQ9, PROs

Free Text various markers (e.g., specific test results)

Other Data Types clinical workflow data

•

• Emerging data types of EHRs that can be integrated/interfaced with internal/external

registries

DATA TYPE EXAMPLE

Biosample Data age, sex/gender, race

Genetic Information diagnosis, severity, medical history

Social Data active diagnosis, resolved diagnosis

Patient-Generated familial disorders, risk factors

Community food and medication allergy, anaphylaxis

Geo-spatial DTaP, HepB, IPV

Surveys Prescriptions written

Free Text inpatient, outpatient

DATA TYPE EXAMPLE

Other Data Types CBC results, HbA1C levels

Sample Use Cases and Architecture of EHR-Based Registries

Registries that incorporate EHR data may use a variety of IT system architectures. Registry architects
must consider the number of participating sites (single-site or multi-site), variety of underlying EHRs
(one enterprise-level EHR, multiple EHR installations of the same vendor, multiple EHRs from
different vendors), existence and connectivity to Health Information Exchanges (HIEs) (centralized,
federated or distributed), and other factors that affect interoperability.
Following are examples of three “hypothetical” EHR-based registry types, each with a different
combination of stakeholders and IT infrastructures. Registries designed to support clinical care are
often based on single enterprise-level EHRs, while registries designed for research are often hosted
external to EHRs but may receive EHR extracts from multiple sources. Public health registries, similar
to registries designed for research, are often hosted by health departments outside of a single EHR
environment but receive EHR reports on a regular basis. Note, these are generalized examples;
actual IT infrastructure and features may vary.

IT infrastructure and other features of sample registry types using EHR data

REGISTRY TO REGISTRY
PUBLIC HEALTH
TYPE/SPECS SUPPORT CLINICAL DESIGNED FOR
REGISTRY
CARE RESEARCH

Depending on the Depending on the Depending on the

Scope provider network’s size: research aim/goal: public health authority:
Local State City
City Regional County
State National State
Regional International National/Federal
National (e.g., VHA)

Stakeholders government (local,

providers (usually research institutes city, county, state or
within the network)
government (local, state federal)
biopharmaceutical and or federal)
medical device
companies [optional] non-profit organization

employers [optional] disease associations

payers [optional]
 REGISTRY TO REGISTRY
PUBLIC HEALTH
TYPE/SPECS SUPPORT CLINICAL DESIGNED FOR
REGISTRY
CARE RESEARCH
biopharmaceutical and
medical device
companies
employers (e.g.,
professional sports)

Sources of Data
mainly EHRs surveys surveys
sometimes EHR-based custom EHR extracts EHRs
patient portals
other data sources (e.g., other data sources
sometimes merged biobanks, (e.g., HIEs,
insurance claims administrative health environmental, health
insurance claims, department,
infrequently EHR- eCRFs, other registries) surveillance systems)
embedded surveys

Number of Usually one enterprise- Multiple/various EHRs Multiple/various EHRs

EHRs level EHR
EHR low high medium
Interoperability
Requirement
EHR Integration usually automated
Level sometimes manual automated for some
(e.g., immunization
frequently semi- records)
automated
manual for others (e.g.,
rarely fully automated non-MU registries)

EHR Integration custom-built APIs /

Tools EHR built-in tools extracts EHR build-in tools for
select reporting (MU
sometimes custom-built program)
APIs / extracts
Custom-built
tools/APIs for non-MU
registries

System EHR-based May not be EHR-based not EHR-based

Dependency
Common Often Centralized
Architecture Centralized Centralized
Distributed Distributed
 REGISTRY TO REGISTRY
PUBLIC HEALTH
TYPE/SPECS SUPPORT CLINICAL DESIGNED FOR
REGISTRY
CARE RESEARCH
Federated Federated

Dominant EHR-embedded (e.g., Could be distributed non-EHR DB (i.e.,

Hosting DB EHR registry data and likely to include public health database)
warehouse) non-EHR DB (i.e.,
research-specific data
collection)
Alternative
Names clinical quality registry product or disease outbreak registries
registry
improvement/measure vaccination registries
registry clinical research
registry disease surveillance
chronic disease (e.g., cancer)
management registry research network
registry
high risk [population]
registry

Typical
Functions clinical workflow evidence for public health services
management effectiveness,
comparative outbreak surveillance
disease/cohort effectiveness, safety
management (e.g., care syndromic surveillance
and/or value for
coordination) clinicians, patients and epidemiological
population health payers research
management (e.g., case natural history of biopharmaceutical
management) disease studies research, e.g., vaccine
effectiveness and
safety

Timeliness
usually real-time mostly periodic (daily, sometimes real-time
weekly or monthly
sometimes periodic extracts) sometimes periodic
(daily extracts) (daily, weekly or
sometimes real-time monthly extracts)

Scalability limited to individual depends on adopting

EHR vendors depends on registry interoperability
architectures adopting standard and future
EHR stages of MU for
interoperability public health reporting
standards
 How OpenEyes Uses Data to Target Marketing Campaigns
• Segmenting their audience: OpenEyes segments their audience based on demographics,
interests, and behavior. This helps them to create more targeted marketing campaigns that
are more likely to reach and engage their target audience. For example, they can target
patients who are interested in a particular type of treatment or who have a certain health
condition.

• Personalizing their messages: OpenEyes personalizes their marketing messages to each

individual patient. This includes using the patient's name, location, and interests in the
messages. For example, they can send a patient a message about a new treatment that is
relevant to their health condition.

• Using A/B testing: OpenEyes uses A/B testing to test different marketing campaigns and
messages to see what works best. This helps them to optimize their campaigns and get the
best results. For example, they can test different headlines, images, and calls to action to see
which ones get the most clicks.

• Tracking the results: OpenEyes tracks the results of their marketing campaigns to see how
effective they are. This helps them to improve their campaigns over time and get better
results. For example, they can track the number of clicks, conversions, and sales generated
by their campaigns

CONCLUSION
OpenEyes is a healthcare organization that uses data analytics to improve all aspects of its business.
They use data to improve patient care, optimize operations, target marketing campaigns, and
improve day-to-day operations.

Use of data analytics has helped healthcare organizations to achieve a number of successes,
including:

 Reduced readmission rates by 10%

 Increased patient satisfaction scores by 5%

 Decreased the cost of supplies by 5%

 Increased the number of patients seen per day by 10%

 Increased the number of marketing leads by 20%

OpenEyes' use of data analytics is a great example of how data can be used to improve healthcare.
By using data to track outcomes, identify risk factors, personalize care, improve communication, and
encourage patient engagement, OpenEyes is able to deliver better care to their patients and improve
their outcomes.