Mental Disorder Screening Via Wearable Internet Of Things: Deep Neural Network Approach

BHAVANA SHRIVASTAVA; Anurag Shrivastava

doi:10.70454/JRICST.2026.30304

Authors

BHAVANA SHRIVASTAVA Assistant Professor, School of Computer Science and Engineering, IILM University, Greater Noida, India Author
Anurag Shrivastava Assistant Professor, School of Computer Science Engineering & Technology, Bennett University, G. Noida, India Author

DOI:

https://doi.org/10.70454/JRICST.2026.30304

Keywords:

Mental disorder screening, Wearable Iota, Lightweight deep neural networks, Physiological signals, Digital mental health

Abstract

Mental health problems are becoming a significant international health issue, and a late diagnosis has, in most cases, caused serious social, economic, and clinical impacts. Early detection is consequently a requirement for timely intervention and better results. The latest developments in wearable Internet of Things (Iota) technology have enabled continuous, non-invasive measurements of physiological indicators, including heart rate variability, sleep behavior, and exercise intensity, and have opened new opportunities for objective mental health measurement. Nevertheless, traditional deep learning-based approaches to the detection of mental disorders are computationally expensive and cannot be deployed on wearable or edge computing devices with limited resources, as they have high latency and consume a lot of energy. This paper suggests deep neural network (DNN) architecture for screening mental disorders using wearable Iota data. The approach to it is pre-processing a set of multi-sensor physiological data, obtaining compact feature representations, and training an optimized DNN with fewer parameters. Accuracy, precision, recall, F1-score, model size, and inference time are the measures of model performance. The suggested solution exhibits accuracy in competitive screening but minimizes the computational load, which is why it is appropriate in the digital application of mental health wearables in real-time.

Downloads

Download data is not yet available.

References

[1] M. Alma, M. M. Raman, and M. A. Husain, “Edge intelligence for wearable health monitoring systems: Opportunities and challenges,” IEEE Access, vol. 11, pp. 35642–35658, 2023.

[2] Y. S. Can, N. Chalabianloo, D. Ekes, and C. Eros, “Continuous stress detection using wearable sensors in real life: Algorithmic programming contest case study,” Sensors, vol. 20, no. 6, p. 1849, Mar. 2020.

[3] Y. Ago, H. Li, and J. Wang, “Hybrid deep learning models for mental health monitoring using wearable physiological signals,” Biomed. Signal Process. Control, vol. 79, p. 104121, Jan. 2023.

[4] D. Hernando, N. Garatachea, R. Almeida, J. A. Casajús, and R. Bail on, “Validation of heart rate variability from wearable devices for stress monitoring,” IEEE J. Biomed. Health Inform. vol. 25, no. 4, pp. 1118–1127, Apr. 2021.

[5] M. S. Husain, G. Muhammad, and N. Guiana, “Explainable AI and edge intelligence for healthcare,” IEEE Network, vol. 35, no. 4, pp. 140–147, Jul. /Aug. 2021.

[6] N. C. Jacobson, H. Weingarten, and S. Wilhelm, “Using digital phenotyping to assess mental health,” Annul. Rev. Clan. Psychol., vol. 20, pp. 1–26, 2024.

[7] H. G. Kim, E. J. Chon, D. S. Bay, Y. H. Lee, and B. H. Koo, “Stress and heart rate variability: A meta-analysis,” Psychiatry Investing., vol. 19, no. 3, pp. 235–245, Mar. 2022.

[8] K. Koneke and R. L. Spitzer, “The PHQ-9: A new depression diagnostic and severity measure,” J. Gen. Intern. Med., vol. 36, no. 2, pp. 410–416, Feb. 2021.

[9] X. Li, Y. Zhang, Zhao, and Z. Chen, “Sleep disturbance and depression detection using wearable sensor data,” Sleep Med., vol. 100, pp. 222–230, Dec. 2023.

[10] Y. Li, R. Wang, and A. T. Campbell, “Digital phenotyping for mental health via wearable and mobile sensing,” NPJ Digit. Med., vol. 7, no. 1, p. 18, 2024.

[11] V. Patel et al., “The Lancet Commission on global mental health and sustainable development,” The Lancet, vol. 402, no. 10398, pp. 219–245, Oct. 2023.

[12] D. F. Santomauro et al., “Global prevalence and burden of depressive and anxiety disorders in 2020 due to the COVID-19 pandemic,” The Lancet, vol. 398, no. 10312, pp. 1700–1712, Nov. 2021.

[13] A. Sharma, W. Verb eke, and S. Van Belle, “Machine learning applications in mental health care: A systematic review,” JMIR Mental Health, vol. 7, no. 6, p. e17884, Jun. 2020.

[14] E. Thompson, S. R. Mishap, and J. Hsu, “Challenges in mental health screening and diagnosis in low-resource settings,” Glob. Mental Health, vol. 9, p. e28, 2022.

[15] World Health Organization, World mental health report: Transforming mental health for all, Geneva, Switzerland: WHO, 2022.

[16] X. CSU et al., “Edge computing-enabled healthcare systems: Challenges and opportunities,” Future Genre. Compute. Syst., vol. 117, pp. 340–352, Apr. 2021.

[17] D. Zhang, X. Ding, Q. Chen, and Y. Zhao, “Deep learning-based stress detection using wearable physiological signals,” Compute. Biol. Med., vol. 143, p. 105312, Apr. 2022.

[18] Y. Zhang, J. Liu, and H. Wang, “Lightweight neural networks for wearable healthcare applications,” IEEE Trans. Ind. Inform., vol. 19, no. 5, pp. 5214–5223, May 2023.

[19] Z. Zhao, Y. Chen, J. Li, and Y. CSU, “Privacy-preserving federated learning for wearable healthcare systems,” IEEE J. Biomed. Health Inform. vol. 28, no. 2, pp. 950–961, Feb. 2024.

[20] L. Zhao, X. Li, and Z. Chen, “Edge-based intelligent systems for digital mental health monitoring,” ACM Computer. Surd. vol. 56, no. 4, pp. 1–38, Jan. 2024.

[21] D. Latino, A. Abu-Mahfouz, and H. My burgh, “Mental disorder assessment in Iota-enabled WBAN systems with dimensionality reduction and deep learning,” J. Sens. Actuator Newt., vol. 14, no. 3, p. 49, 2025, doe: 10.3390/jsan14030049.

[22] S. Edam, P. Parana, and S. Data, “A deep learning approach with wearable physiological sensors and feature selection methods to detect mental stress in Indian housewives,” Disco. Art if. Intel. vol. 6, p. 113, 2026, doe: 10.1007/s44163-026-00837-9.

[23] S. Ghost, S. Kim, M. F. Jazz, P. K. Singh, and M. Mahmud, “Classification of mental stress from wearable physiological sensors using image-encoding-based deep neural network,” Biosensors, vol. 12, no. 12, p. 1153, Dec. 2022, doe: 10.3390/bios12121153.

[24] A. Mandela and S. Chakravarthi Lade, “A review on IoT-cloud based EEG depression detection system: A case study,” Int. J. Intell. Syst. Appl. Eng., vol. 12, no. 20s, pp. 814–819, 2024. [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/5306

[25] A. Abd-Alrazaq, R. AlSaad, and F. Shuweihdi, “Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression,” NPJ Digit. Med., vol. 6, p. 84, 2023, doi: 10.1038/s41746-023-00828-5.

[26] F. M. Talaat and R. M. El-Balka, “Stress monitoring using wearable sensors: IoT techniques in medical field,” Neural Comput. Applic., vol. 35, pp. 18571–18584, 2023, doi: 10.1007/s00521-023-08681-z.

[27] A. V. Caragață et al., “Smart devices and multimodal systems for mental health monitoring: From theory to application,” Bioengineering, vol. 13, no. 2, p. 165, 2026, doi: 10.3390/bioengineering13020165.