AI-Powered Behavioral Health Monitoring in Telemedicine Platforms: A 72-Hour Early Warning Framework Using Passive Digital Biomarkers and LSTM Networks
DOI:
https://doi.org/10.68314/4akfkj55Keywords:
Telemedicine, Behavioral Health, Digital Biomarkers, LSTM, Early Warning System, Clinical Decision Support, Passive Sensing, TIHM DatasetAbstract
Requiring patients to complete screening questionnaires periodically is a challenge for early detection of deterioration in behavioral health in telemedicine. This study suggests an Artificial Intelligence system that uses Passive Digital Biomarkers, derived from multimodal sensing from remote monitoring devices, to be integrated at the feature-level to predict behavioral health events 72 hours ahead of time. The data used were from the TIHM dataset with 56 patients and 5,096 patient day records, from which we engineered 15 features encompassing activity patterns, sleep architecture, and physiological signals. We benchmarked baseline machine learning models (Logistic Regression, Random Forest, Gradient Boosting) with a temporal Long Short-Term Memory (LSTM) network with an input window of 7 days. The model performance was assessed with area under the receiver operating characteristic curve (AUC-ROC), Brier score for calibration, and statistical comparison through a null-centered bootstrap approximation to DeLong's test. The LSTM model achieved significantly higher discrimination (AUC = 0.808) compared to the best baseline (Random Forest: AUC = 0.711; ΔAUC = −0.097, 95% CI [−0.142, −0.052], p < 0.001). The model gave a median warning lead time of 1.0 day with a tolerable false positive rate at a clinically calibrated threshold to achieve 90% sensitivity. Multimodal passive sensing, coupled with temporal deep learning, holds great promise for more precise and earlier behavioral health monitoring, but requires external validation with a larger sample size. The proposed framework sets a repeatable and privacy-friendly groundwork for proactive telemedicine interventions.
References
Beutel, D. J., et al., “Flower: A friendly federated learning research framework,” arXiv:2007.14390, 2020, doi: 10.48550/arXiv.2007.14390.
Bi, S., et al., “Predicting depression risk in middle-aged and elderly adults in China using CNN-BiLSTM-Attention mechanism and LSTM+SHAP framework,” BMC Psychiatry, vol. 25, Art. no. 787, 2025, doi: 10.1186/s12888-025-07178-4.
Che, Z., S. Purushotham, K. Cho, D. Sontag, and Y. Liu, “Recurrent neural networks for multivariate time series with missing values,” Sci. Rep., vol. 8, Art. no. 6085, 2018, doi: 10.1038/s41598-018-24271-9.
Chicco, D., and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, Art. no. 6, 2020, doi: 10.1186/s12864-019-6413-7.
Efron, B., and R. J. Tibshirani, An Introduction to the Bootstrap. New York, NY, USA: Chapman & Hall/CRC, 1993.
Friedman, J. H., “Greedy function approximation: A gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001. [Online]. Available: https://www.jstor.org/stable/2699986
IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems, Ethically Aligned Design: A Vision for Prioritizing Human Well-being with Autonomous and Intelligent Systems, 1st ed. Piscataway, NJ, USA: IEEE, 2019. [Online]. Available: https://standards.ieee.org/wp-content/uploads/import/documents/other/ead_v2.pdf
Insel, T. R., “Digital phenotyping: Technology for a new science of behavior,” JAMA, vol. 318, no. 13, pp. 1215–1216, 2017, doi: 10.1001/jama.2017.11295.
Jacobson, N. C., and Y. J. Chung, “Passive sensing of prediction of moment-to-moment depressed mood among undergraduates with clinical levels of depression using smartphones,” Sensors, vol. 21, no. 11, Art. no. 3771, 2021, doi: 10.3390/s21113771.
Jacobson, N. C., H. Weingarden, and S. Wilhelm, “Digital biomarkers of mood disorders and symptom change,” NPJ Digit. Med., vol. 2, Art. no. 3, 2019, doi: 10.1038/s41746-019-0078-0.
Kroenke, K., R. L. Spitzer, and J. B. Williams, “The PHQ-9: validity of a brief depression severity measure,” J. Gen. Intern. Med., vol. 16, no. 9, pp. 606–613, 2001, doi: 10.1046/j.1525-1497.2001.016009606.x.
Lim, B., S. Ö. Arık, N. Loeff, and T. Pfister, “Temporal fusion transformers for interpretable multi-horizon time series forecasting,” Int. J. Forecast., vol. 37, no. 4, pp. 1748–1764, 2021, doi: 10.1016/j.ijforecast.2021.03.012.
Martinez-Martin, N., H. T. Greely, and M. K. Cho, “Ethical development of digital phenotyping tools for mental health applications: Delphi study,” JMIR Mhealth Uhealth, vol. 9, no. 7, Art. no. e27343, 2021, doi: 10.2196/27343.
McMahan, H. B., E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Proc. 20th Int. Conf. Artif. Intell. Stat. (AISTATS), vol. 54, 2017, pp. 1273–1282, doi: 10.48550/arXiv.1602.05629.
Mohr, D. C., M. Zhang, and S. M. Schueller, “Personal sensing: Understanding mental health using ubiquitous sensors and machine learning,” Annu. Rev. Clin. Psychol., vol. 13, pp. 23–47, 2017, doi: 10.1146/annurev-clinpsy-032816-044949.
Noci, F., L. Agrawal, A. Achtari, and P. Meyer, “Wearable technologies to predict and prevent heart failure hospitalizations: A systematic review,” Eur. Heart J. Digit. Health, vol. 6, no. 5, pp. 868–877, 2025, doi: 10.1093/ehjdh/ztaf079.
Onnela, J. P., and S. L. Rauch, “Harnessing smartphone-based digital phenotyping to enhance behavioral and mental health,” Neuropsychopharmacology, vol. 41, no. 7, pp. 1691–1696, 2016, doi: 10.1038/npp.2016.7.
Oudin, A., et al., “Digital phenotyping: Data-driven psychiatry to redefine mental health,” J. Med. Internet Res., vol. 25, Art. no. e44502, 2023, doi: 10.2196/44502.
Palermo, F., et al., “TIHM: An open dataset for remote healthcare monitoring in dementia,” Sci. Data, vol. 10, Art. no. 606, 2023, doi: 10.1038/s41597-023-02519-y.
Ramesh, K., et al., “Machine learning prediction of agitation in dementia patients using sleep and physiological data,” Appl. Sci., vol. 15, no. 18, Art. no. 9908, 2025, doi: 10.3390/app15189908.
Rostill, H., et al., “Technology integrated health management for dementia,” Br. J. Community Nurs., vol. 23, no. 10, pp. 502–508, 2018, doi: 10.12968/bjcn.2018.23.10.502.
Saeb, S., et al., “Mobile phone sensor correlates of depressive symptom severity in daily-life behavior: An exploratory study,” J. Med. Internet Res., vol. 17, no. 7, Art. no. e175, 2015, doi: 10.2196/jmir.4273.
Shatte, A. B. R., D. M. Hutchinson, and S. J. Teague, “Machine learning in mental health: A scoping review of methods and applications,” Psychol. Med., vol. 49, no. 9, pp. 1426–1448, 2019, doi: 10.1017/S0033291719000151.
Sutton, R. T., et al., “An overview of clinical decision support systems: Benefits, risks, and strategies for success,” NPJ Digit. Med., vol. 3, Art. no. 17, 2020, doi: 10.1038/s41746-020-0221-y.
Tomašev, N., et al., “A clinically applicable approach to continuous prediction of future acute kidney injury,” Nature, vol. 572, no. 7767, pp. 116–119, 2019, doi: 10.1038/s41586-019-1390-1.
Torous, J., K. J. Myrick, N. Rauseo-Ricupero, and J. Firth, “Digital mental health and COVID-19: Using technology today to accelerate the curve on access and quality tomorrow,” JMIR Ment. Health, vol. 7, no. 3, Art. no. e18848, 2020, doi: 10.2196/18848.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dr. Sumanth Banakar, Dr. Venkatesh Ankarla Sri Ramuloo, Dr. Kasi Viswanath Bolla, Dr. Greg M. Benson, Lourdu Akhila Yeruva, Rohit Reddy Gaddam (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.