TABLE OF CONTENTS

1. INTRODUCTION 2

2. LITERATURE REVIEW 2

3. RESEARCH GAP 11

4. PROBLEM STATEMENT 12

5. OBJECTIVE 13

6. REFERENCES 13

Introduction
Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 1

In monitoring mental health, wearable technology has rapidly emerged as a transformative tool.
Physiological monitoring devices, including smartwatches and activity trackers, are becoming
part of daily life, and the unprecedented opportunities they offer for real-time monitoring of
mental health should be analyzed and studied with great importance. These devices track
physiological signals that serve as critical indicators of mental health conditions, such as anxiety
disorder, stress, and depression by detecting heart rate variability (HRV), electrodermal activity
(EDA), and sleep patterns. Recently, there has been an increasing number of research studies
investigating the potential of wearable technologies to provide continuous and objective
assessments of mental health. This interest was accelerated in search of a solution to overcome
limitations in traditional approaches to mental health assessment, which generally involve self-
report data and/or clinical evaluations, which may be biased and occur infrequently. Wearables
can track live data, thus making interventions not just more dynamic but also very early, which
may improve outcomes in persons with mental health conditions.

However, integrating wearable technology into mental health care also presents challenges such
as data accuracy, privacy concerns, and generalizability issues in machine learning models across
diverse populations. Ethical implications for continuous monitoring and data misuse are very
critical considerations that should be taken into account as this technology is increasingly used.

Literature

Reference Title of Paper Relevance Gaps Tentative

Approach

[2] Predicting Stress Central to real- Limited real-world Expand real-world

Levels Using time stress testing, data testing, improve
Physiological monitoring via accuracy issues, accuracy, and
Data: Real-Time wearables. small datasets. develop
Stress Prediction comprehensive
Models Utilizing datasets.
Wearable Devices

[3] Integrating Use of Lack of large-scale Conduct large

Smartwatches in smartwatches for trials, ethical trials, address

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 2

Community mental health concerns, need for ethics, and

Mental Health monitoring. personalization. personalize
Services for Severe interventions.
Mental Illness

[31] Identifying Identifies stress Homogeneous Broaden sample

Objective markers using sample, no diversity, explore
Physiological wearables, exploration of causal links
Markers and relevant to causal models. between stress and
Modifiable objective mental mental health.
Behaviors for Self- health
Reported Stress monitoring.
and Mental Health
Status

[32] Wearable Sensing Key to Lacks detail on Focus on sensor

Systems for continuous, sensor miniaturization,
Monitoring Mental objective mental miniaturization, advanced
Health health algorithm algorithms, and
monitoring. development, ethical use.
ethical
considerations.

[54] Mental Health Overview of Need for broader Broaden sensing

Monitoring with multimodal sensing modalities, research and
Multimodal sensing, challenges in improve automated
Sensing and important for automation. monitoring
Machine Learning: covering diverse systems.
A Survey monitoring
technologies.

[58] Explore the Examines Limited Study clinical

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 3

Integration of integration of understanding of relevance, address

Sensor-Captured wearable data in clinical relevance, adoption barriers.
Patient-Generated clinical mental adoption barriers.
Data in Mental health settings.
Health Care for
Veterans

[33] PRISM: A Data- Platform for Challenges in Enhance data

Driven Platform continuous integrating integration
for Monitoring monitoring, subjective and techniques for
Mental Health crucial for objective data. continuous
developing new monitoring.
tech in mental
health.

[59] Anxiety Level Relevant for Needs better real- Improve real-time
Recognition for innovative use of time anxiety assessment in VR
Virtual Reality wearables in assessment and therapy, focus on
Therapy System mental health personalized personalized
Using therapy. interventions. interventions.
Physiological
Signals

[46] Continuous Relevant for Noise in Develop noise-

Physiological developing biosignals, filtering techniques
Monitoring Using mental health overlapping for better accuracy
Wearable monitoring physiological in monitoring.
Technology to applications. responses.
Inform Individual
Management of
Infectious Diseases

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 4

[41] Wearable Eye Novel insights Insufficient long- Focus on long-term

Tracking into mental term use research, use studies,
Technology for health lack of automated develop automated
Mental Health monitoring via analysis analysis algorithms
Monitoring eye tracking. algorithms. for eye tracking
data.

Table 1: Most Relevant 10 Papers from the Research

Research Area Gaps Identified Proposed Future Directions

Stress Detection Real-time data, noise Standardized datasets

Depression Monitoring Ethical issues, privacy Larger population studies

Anxiety Detection Longitudinal data Multimodal data integration

General Wearable Tech User-independent models, validation Explainable AI, user studies

Table 2: Key Insights from Survey Research

Study Focus Data Type ML Techniques Key Findings Challenges

Stress Heart Rate LSTM, Bi- Improved stress Real-time data

Detection Variability, LSTM detection collection, noise
EDA accuracy removal

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 5

Depression Sleep Patterns, Random Forests, Early detection Lack of standardized

Monitoring Activity Levels SVM of depression datasets, ethical
concerns

Anxiety EEG Signals LDA, KNN, Promising results Need for better
Detection SVM in anxiety feature extraction
detection methods

Emotion Physiological Deep Learning, High accuracy in Need for multi-

Detection Signals Ensemble emotion modal, user-
Approaches prediction independent models

Real-time Multimodal Bi-LSTM, Long-term Integration of

Monitoring Sensor Data Probabilistic disease multimodal data,
Ontologies management lack of clinical
validation

Table 3: Summary of key findings in wearable technology for mental health monitoring

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 6

Figure 1: Number of Research Papers by Year

From Figure 1, it can be understood the number of published articles year by year from 2012 to
2024, which showed a dramatic high peak in the year 2024 with the number of 30 papers. Other
years that also have rather high results are the year 2020 and the year 2021 with 10 and 5 papers
each, respectively. Other years like 2023, 2022, 2018 have quite low counts that ranges about 3-4
papers. All the three years have only 1 paper, which cautions that all the three years under
consideration have low level of research productivity. From the above chart the number of
publications increases year by year and steeply rises in 2024.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 7

Figure 2: Distribution of Research Topics

In Figure 2, wearable devices have been identified to take the bigger share of research in the field
at 27%. 6%: The primary area that has witnessed much focus is the development and use of
technologies for wearables for monitoring mental health factors including heart rates and sleep
patterns. Next is stress detection, which makes up twenty-four percent. Thus, 1% of the research
shows just how significant is the support of stress level variations through physiological signals.
Other important ones include the assessment of depressive symptoms, a process that is
completed in twenty. It has been noted that 7% of the studies have followed up the symptoms
through the use of wearables. About 17. There were two percent of the studies on the AI models
that also indicate how these devices incorporate artificial intelligence into analytics that could
potentially diagnose conditions in mental health or predict them. The last category is “Others”
with approximately 10 percent of the total population. 3%, because in this case it will be the
number of topics, which will be newly developing or rather specific within the field. The said
distribution therefore points toward practical emphasis of the issue, thus incorporating

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 8

technology into mental health, particularly managing stress and depression, along with the
emerging involvement of AI in this field.

Figure 3: Trends in Research Focus Over Time

Figure 3 depicts the trends of the research focus throughout three key areas: Growth of Wearable
Devices, AI Models, and Stress Monitoring Between 2020 and 2024. From this trend, it is
possible to point out an upward trend in all the three, which indicates the interest in these
research aspects is rising. Wearable Devices and Stress Monitoring had a small beginning with
the number of papers in the year 2020 and wonderfully exhibited a very steep climb from the
year 2021 for Stress Monitoring which has become the maximum by the year 2024. The use of
AI models reached the momentum at the beginning and showed the highest growth in 2022,
though it declined in 2023, but may have a continental rise in 2024. The curve above shows that
all areas are becoming more important, essentially indicating that the trend of its research has
been most heightened and quite realistic in the aspect of Stress Monitoring, a concept of
monitoring one’s health status.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 9

Figure 4: ML techniques in mental health monitoring

Figure 4 represents the ML techniques that are used for monitoring stress and anxiety; others like
LSTM, SVM, Random forest, KNN, Deep learning are also the same which are represented in
Figure 2 most of the time their application is to monitor stress, anxiety and depression,
sometimes stress. It can also be further emphasized from the graph that, especially for stress
detection, LSTM models are dominant, which might be attributed to the fact that LSTM are
particularly good at handling time series data- an important feature when working with
physiological signals such as the HRV. The rest of the machine learning techniques considered
in this overview, namely, SVM and Random Forests, are also used under all three conditions
since they proved to be versatile and rather effective in classification tasks with this kind of
complex and high-dimensional data. KNN and deep learning techniques used and with slightly
lower frequency of occurrence. From this chart, one can understand that present research deals
with improving the accuracy and reliability of wearables-based mental health monitoring through
the help of ML while pointing to the directions for future research such as the utilization of deep
learning models for anxiety detection and stress monitoring.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 10

Research Gaps

Important gaps in the survey paper on wearable technology for mental health monitoring are
identified. It is stressed that there is a tacking of important areas that would close these gaps to
improve the technology toward effectiveness and increased adoption.

First and foremost, there is a huge difference in data integration between signal categories: most
of the current research considers physiological, behavioral, and linguistic data as practically
separate sources and does not combine them to provide a more general impression of the mental
state of an individual. Future research needs to work on the development of one comprehensive
model that unites different data types, since such a model will enhance both the accuracy and
depth of mental health assessment.

The other major gap involves real-world validation. Most of the research on this topic is
conducted under controlled or laboratory conditions, which are pretty far from the real diverse,
uncontrolled environments in which wearable technology would be used. Consequently, very
limited generalization will emanate from these studies. In this regard, future studies warrant
wearable device testing under real-world conditions for effectiveness across diverse populations
and settings.

The paper necessarily needs an in-depth exploration with regard to the ethical and privacy
considerations that have to be attached to physiological data collected on a continuous basis by
these devices. Setting up robust ethical frameworks and ensuring data privacy are cardinal for
gaining user trust and promoting wide dissemination of wearable technology for monitoring
mental health.

The problem is also linked to the generalization ability of machine learning models used in
wearable technology.

Many models lack adaptability across diverse populations and physiological baselines, which
limits their reliability. To address this, future research should focus on developing models that
can adjust to variations in individuals’ physiological and behavioral data, thereby improving the
accuracy of mental health predictions.

Other key gaps include the need for longitudinal data collection and user compliance. Very few
studies have used more than single-session or short-term data, which cannot represent the
dynamic nature of a mental health condition. Future studies should therefore target long-term

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 11

studies that may provide more comprehensive insights into the trend variations in mental health
over time, along with strategies to ensure the engagement of the users with wearable devices.

Another limitation emphasized by the survey is the lack of multimodal data fusion. Few studies
combine multiple physiological signals, such as heart rate variability, sleep data, and
electrodermal activity, into a single framework. Developing techniques that can effectively fuse
these data sources will improve the predictive power and usefulness of wearable technology for
mental health.

Most of all, it is in dire need of standard datasets and large-scale clinical trials. The availability
of non-standard datasets restricts the capability of machine learning models to learn, and without
large-scale clinical validation, applicability in the real world remains unproven for these
technologies. This knowledge gap might be much more important to cross for raising not only
the reliability of wearable technologies but also their wider clinical usage.

Although highly promising, wearable technology has immense potential in mental health
monitoring. Therefore, addressing the gaps identified herein will be important in terms of taking
the field forward and realizing the full potential of such technologies both in clinical and real-
world settings.

Problem Statement

The increased penetration of wearable technology in healthcare, especially in the monitoring of

mental health, has presented great opportunities for the continuous tracking of physiological
signals related to anxiety, stress, and depression in real time. Despite their promising use, several
major challenges impede their widespread adoption into clinical practice. Such challenges
include those related to data accuracy, privacy concerns, generalizability across various
populations with respect to machine learning models, and finally, those involving a lack of
standardized datasets. But apart from that, continuous monitoring and biases in relation to AI
pose some major ethical obstacles to effective wearables in mental health care.

These challenges are to be identified through this research survey, critically assessed, and some
possible future research directions put forward that might enable wearable devices for more
accurate, reliable, and ethical personalized mental health interventions. This report seeks to
answer two questions: how machine learning models can be developed to overcome these
challenges and how engineers, clinicians, and ethicists can work collaboratively to develop and
integrate such technologies into real-world mental health practices.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 12

Objective

The given survey paper critically reviews the advances made and challenges in integrating
wearable technology with machine learning for real-time monitoring of mental health. This
survey aims at finding out how effectively devices worn on the body can identify and manage
mental disorders like anxiety, stress, and depression by analyzing physiological and behavioral
data.

Attention will also be paid to major areas of research gap in the existing literature. These include
data accuracy issues, privacy concerns, generalization across diverse populations, and a lack of
standardized datasets. Other ethical problems which the paper will discuss involve continuous
monitoring, data privacy, consent, and bias in AI models. The paper goes on to propose further
research in the field, emphasizing those very important aspects of study in the need for user-
independent and explainable AI models and the validation of wearable technology in clinical
settings if such technologies are to be used more widely. Further, the paper discusses the role of
collaboration between data scientists, clinicians, and ethicists in making wearable devices a
valid, scalable tool that is ethical to use for personalized interventions in mental health. It finally
attempts to give an overview of how wearable technologies can help in the improvement of
mental health outcomes while addressing various challenges-both technical and ethical-standing
in the way of integration into healthcare systems.

References

[1] Dylan, S. "Wearable Sensor Data Analysis for Mental Health Monitoring." (2024)

[2] Lazarou, Evgenia, and Themis P. Exarchos. “Predicting Stress Levels Using Physiological
Data: Real-Time Stress Prediction Models Utilizing Wearable Devices.” AIMS Neuroscience,
vol. 11, no. 2, AIMS Press, Jan. 2024

[3]Johnston, David, et al. “Integrating Smartwatches in Community Mental Health Services for
Severe Mental Illness for Detecting Relapse and Informing Future Intervention: A Case Series.”

[4]O’Leary, Aisling, et al. “Using Wearable Digital Devices to Screen Children for Mental
Health Conditions: Ethical Promises and Challenges.” Sensors (Basel, Switzerland), vol. 24, no.
10, May 2024,

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 13

[5]Arora, Anshika. “IoT-Enabled Smart Mental Health Assessment Using Deep Hybrid
Regression Models over Actigraph-Based Sequential Motor Activity Data.” Arabian Journal for
Science and Engineering, Springer Science+Business Media, Feb. 2024,

[6]Singh, Vipul1; Sarkar, Sharmila2; Gaur, Vikas3; Grover, Sandeep4; Singh, Om Prakash5. ”
Clinical Practice Guidelines on using artificial intelligence and gadgets for mental health and
well-being”. Indian Journal of Psychiatry 66(Suppl 2):p S414-S419, January 2024. |

[7]Sharada Adepua, Keerthana Pravallika Samudralab, Spandana Kamsani and Sravanthi

Aruvanti."Smart Technology for Real-time Evaluation of Stress Levels".

International Conference on Environmental Development Using Computer Science

(ICECS’24)Volume 491, 21 February 2024

[8]Assessing Anxiety Disorders Using Wearable Devices: Challenges and Future Directions.

[9]A scoping review on monitoring mental health using smart wearable devices

[10]A Survey onWearable Sensors for Mental Health Monitoring

[11] Blake Anthony Hickey, Taryn Chalmers, Phillip Newton, Chin-Teng Lin, David Sibbritt,
Craig S. McLachlan, Roderick Clifton-Bligh, John Morley and Sara Lal.“Smart Devices and
Wearable Technologies to Detect and Monitor Mental Health Conditions and Stress:
ASystematic Review”

[12] Talha Iqbal, Andrew J. Simpkin, Davood Roshan, Nicola Glynn, John Killilea, Jane Walsh,
Gerard Molloy, Sandra Ganly, Hannah Ryman, Eileen Coen, Adnan Elahi, William Wijns and
Atif Shahzad.”Stress Monitoring Using Wearable Sensors: A Pilot Study and Stress-Predict
Dataset”

[13] Pardamean, Bens, et al. “Quantified Self-Using Consumer Wearable Device: Predicting
Physical and Mental Health.” Healthcare Informatics Research, vol. 26, no. 2, Apr. 2020, pp.
83–92.

[14]Garcia-Ceja, Enrique, et al. “Mental Health Monitoring with Multimodal Sensing and
Machine Learning: A Survey.” Pervasive and Mobile Computing, vol. 51, Dec. 2018, pp. 1–26,.

[15]Gedam, Shruti, and Sanchita Paul. “A Review on Mental Stress Detection Using Wearable
Sensors and Machine Learning Techniques.” IEEE Access, vol. 9, 2021, pp. 84045–66.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 14

[16]Mohr, David C., et al. “Personal Sensing: Understanding Mental Health Using Ubiquitous
Sensors and Machine Learning.” Annual Review of Clinical Psychology, vol. 13, no. 1, May
2017, pp. 23–47.

[17]Ali, Farman, et al. “An Intelligent Healthcare Monitoring Framework Using Wearable
Sensors and Social Networking Data.” Future Generation Computer Systems, vol. 114, Jan.
2021, pp. 23–43.

[18]“Emotion Recognition for Everyday Life Using Physiological Signals from Wearables: A
Systematic Literature Review.”.

[19]Alhejaili, Reham, and Akram Alomainy. “The Use of Wearable Technology in Providing
Assistive Solutions for Mental Well-Being.” Sensors (Basel, Switzerland), vol. 23, no. 17, Aug.
2023, p. 7378.

[20]Koinis, Lianne, et al. A Commentary on the Potential of Smartphones and Other Wearable
Devices to Be Used in the Identification and Monitoring of Mental Illness. no. 24, Dec. 2022, pp.
1420–20.

[21] Derdiyok, Seyma, et al. “Neurophysiological and Biosignal Data for Investigating
Occupational Mental Fatigue: MEFAR Dataset.” Data in Brief, vol. 52, Feb. 2024, p. 109896,

[22]Tian, Zhou, and Deng Yi. “Application of Artificial Intelligence Based on Sensor Networks
in Student Mental Health Support System and Crisis Prediction.” Measurement. Sensors,
Elsevier BV, Feb. 2024, pp. 101056–56,Accessed 13 May 2024.

[23]Pedro Elkind Velmovitsky, et al. “Application of a Mobile Health Data Platform for Public
Health Surveillance: A Case Study in Stress Monitoring and Prediction.” Digital Health, vol. 10,
SAGE Publishing, Jan. 2024.

[24]Khoo, Lin Sze, et al. “Machine Learning for Multimodal Mental Health Detection: A
Systematic Review of Passive Sensing Approaches.” Sensors, vol. 24, no. 2, Jan. 2024, p. 348.

[25]Gopalakrishnan, Abinaya, et al. “A Survey of Autonomous Monitoring Systems in Mental

Health.” Wiley Interdisciplinary Reviews. Data Mining and Knowledge Discovery/Wiley
Interdisciplinary Reviews. Data Mining and Knowledge Discovery, 24 Jan. 2024.

[26]G, Jayanthi, et al. “Comparative Analysis of Psychological Stress Detection: A Study of

Artificial Neural Networks and Cat Boost Algorithm.” International Journal of Intelligent
Systems and Applications in Engineering, vol. 12, no. 1, 2024, pp. 385–94..Accessed 24 July
2024.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 15

[‌ 27]Qadeer, S., Memon, K., & Palli, G. H. (2024). Predicting depression and suicidal tendencies
by analyzing online activities using machine learning in android devices. Mehran University
Research Journal Of Engineering & Technology, 43(1), 213–224.

[28]Mashael Aldayel, and Abeer Al-Nafjan. “A Comprehensive Exploration of Machine

Learning Techniques for EEG-Based Anxiety Detection.” PeerJ, vol. 10, PeerJ, Inc., Jan. 2024,
pp. e1829–29. Accessed 20 Mar. 2024.

[29]Berrenur Saylam, and Özlem Durmaz İncel. “Multitask Learning for Mental Health:
Depression, Anxiety, Stress (DAS) Using Wearables.” Diagnostics, vol. 14, no. 5, 26 Feb. 2024,
pp. 501–501.

[30]Abd-alrazaq, Alaa, et al. “Wearable Artificial Intelligence for Anxiety and Depression:
Scoping Review.” Journal of Medical Internet Research, vol. 25, Jan. 2023, p. e42672.

[31]Sano, Akane, et al. "Identifying objective physiological markers and modifiable behaviors
for self-reported stress and mental health status using wearable sensors and mobile phones:
observational study." Journal of medical Internet research 20.6 (2018): e210.

[32]Kang, Mijeong, and Kyunghwan Chai. "Wearable sensing systems for monitoring mental
health." Sensors 22.3 (2022): 994.

[33]Kamdar, Maulik R., and Michelle J. Wu. "PRISM: a data-driven platform for monitoring
mental health." Biocomputing 2016: Proceedings of the Pacific Symposium. 2016.

[34]Hassantabar, Shayan, et al. "Mhdeep: Mental health disorder detection system based on
wearable sensors and artificial neural networks." ACM Transactions on Embedded Computing
Systems 21.6 (2022): 1-22.

[35]Mandal, Anurag, et al. "AI-based Detection of Stress using Heart Rate Data obtained from
Wearable Devices." Procedia Computer Science 230 (2023): 749-759.

[36]Sheikh, Mahsa, Meha Qassem, and Panicos A. Kyriacou. "Wearable, environmental, and
smartphone-based passive sensing for mental health monitoring." Frontiers in digital health 3
(2021): 662811.

[37] Wang, Wei, et al. "Integration of Artificial Intelligence and Wearable Internet of Things for
Mental Health Detection." International Journal of Cognitive Computing in Engineering 5
(2024): 307-315.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 16

[38] Saito, Tomoki, Hikaru Suzuki, and Akifumi Kishi. "Predictive modeling of mental illness
onset using wearable devices and medical examination data: Machine learning approach."
Frontiers in digital health 4 (2022): 861808.

[39]Robinson, Tony, et al. "Self-Management of Subclinical Common Mental Health Disorders

(Anxiety, Depression and Sleep Disorders) Using Wearable Devices." International journal of
environmental research and public health 20.3 (2023): 2636.

[40]Lazarou, Evgenia, and Themis P. Exarchos. "Predicting stress levels using physiological
data: Real-time stress prediction models utilizing wearable devices." AIMS Neuroscience 11.2
(2024): 76-102.

[41] Vidal, Mélodie, et al. "Wearable eye tracking for mental health monitoring." Computer
Communications 35.11 (2012): 1306-1311.

[42] Moshe, Isaac, et al. "Predicting symptoms of depression and anxiety using smartphone and
wearable data." Frontiers in psychiatry 12 (2021): 625247.

[43]Xu, Gelei, et al. "An Adaptive System for Wearable Devices to Detect Stress Using
Physiological Signals." arXiv preprint arXiv:2407.15252 (2024).

[44]Vos, Gideon, et al. "Generalizable machine learning for stress monitoring from wearable
devices: A systematic literature review." International Journal of Medical Informatics 173
(2023): 105026.

[45] Pedrelli, Paola, et al. "Monitoring changes in depression severity using wearable and mobile
sensors." Frontiers in psychiatry 11 (2020): 584711

[46]Ming, Damien K., et al. “Continuous Physiological Monitoring Using Wearable Technology
to Inform Individual Management of Infectious Diseases, Public Health and Outbreak
Responses.” International Journal of Infectious Diseases, vol. 96, July 2020, pp. 648–54.
Accessed 7 Feb. 2021.

[47]Debard, Glen, et al. “Making Wearable Technology Available for Mental Healthcare through
an Online Platform with Stress Detection Algorithms: The Carewear Project.” Journal of
Sensors, edited by Christos Riziotis, vol. 2020, Nov. 2020, pp. 1–15.

[48]Pakhomov, Serguei V. S., et al. “Using Consumer-Wearable Technology for Remote

Assessment of Physiological Response to Stress in the Naturalistic Environment.” PLOS ONE,
edited by Manuela Cabiati, vol. 15, no. 3, Mar. 2020, p. e0229942.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 17

[49]Griffin, Benjamin, and Kate E. A. Saunders. “Smartphones and Wearables as a Method for
Understanding Symptom Mechanisms.” Frontiers in Psychiatry, vol. 10, Jan. 2020, Accessed 23
May 2020.

[50]Coutts, Louise V., et al. “Deep Learning with Wearable Based Heart Rate Variability for
Prediction of Mental and General Health.” Journal of Biomedical Informatics, vol. 112, Dec.
2020, p. 103610.

[51]Sano, Akane, et al. “Identifying Objective Physiological Markers and Modifiable Behaviors
for Self-Reported Stress and Mental Health Status Using Wearable Sensors and Mobile Phones:
Observational Study.” Journal of Medical Internet Research, vol. 20, no. 6, June 2018, p. e210.

[52]Taj-Eldin, Mohammed, et al. “A Review of Wearable Solutions for Physiological and

Emotional Monitoring for Use by People with Autism Spectrum Disorder and Their Caregivers.”
Sensors, vol. 18, no. 12, 4 Dec. 2018, p. 4271.

[53]Cormack, Francesca, et al. “Wearable Technology for High-Frequency Cognitive and Mood
Assessment in Major Depressive Disorder: Longitudinal Observational Study.” JMIR Mental
Health, vol. 6, no. 11, 18 Nov. 2019, p. e12814.

[54]Garcia-Ceja, Enrique, et al. “Mental Health Monitoring with Multimodal Sensing and
Machine Learning: A Survey.” Pervasive and Mobile Computing, vol. 51, Dec. 2018, pp. 1–26,
www.sciencedirect.com/science/article/pii/S1574119217305692,

[55]Bari, Rummana, et al. “Automated Detection of Stressful Conversations Using Wearable

Physiological and Inertial Sensors.” Proceedings of the ACM on Interactive, Mobile, Wearable
and Ubiquitous Technologies, vol. 4, no. 4, 17 Dec. 2020, pp. 1–23. Accessed 15 Aug. 2021.

[56]Ulziibayar, Natsagdorj, et al. “Human Mental Condition Monitoring through Measurement

of Physiological Signals.” Journal of Korea Multimedia Society, vol. 23, no. 9, 2020, pp. 1147–
54.Accessed 4 Oct. 2021.

[57]Patlar Akbulut, Fatma, et al. “Wearable Sensor-Based Evaluation of Psychosocial Stress in

Patients with Metabolic Syndrome.” Artificial Intelligence in Medicine, vol. 104, Apr. 2020, p.
101824.Accessed 22 Oct. 2022.

[‌ 58]Ng, Ada, et al. Provider Perspectives on Integrating Sensor-Captured Patient-Generated

Data in Mental Health Care. Vol. 3, no. CSCW, 7 Nov. 2019, pp. 1–25.

Department of Computer Science, CHRIST (Deemed to be University)

Wearable Tech In Mental Health: A Comprehensive Review of Monitoring and Machine Learning Applications 18

[59]Šalkevicius, Justas, et al. “Anxiety Level Recognition for Virtual Reality Therapy System
Using Physiological Signals.” Electronics, vol. 8, no. 9, Sept. 2019, p. 1039. Accessed 5 May
2020.

[‌ 60]Sevil, Mert, et al. “Detection and Characterization of Physical Activity and Psychological
Stress from Wristband Data.” Signals, vol. 1, no. 2, 4 Dec. 2020, pp. 188–208.Accessed 9 June
2022.

Department of Computer Science, CHRIST (Deemed to be University)