International Journal of Drug Delivery Technology
Volume 16, Issue 8s, 2026

ML and AI predictive modeling and continuous patient surveillance for chronic disease prevention using electronic health records and IoT-based data streams

Dr. Sachin Kumar Murarka1, Neha Jain2, Dr. Vivek Sharma3, Ajay Malhosia4, Vibhav Krashan Chaurasiya5

1Department of Computer Science and Information Technology, Sagar Institute of Research and Technology, Bhopal, India
Email: sachin.it@sirtbhopal.ac.in

2Computer Science and Engineering, Jai Narain College of Technology, Bhopal (M.P.), India
Email: nehar2020j@gmail.com

3Computer Science and Engineering, Jai Narain College of Technology, Bhopal, M.P., India
Email: sharvivek1968@gmail.com

4Jai Narain College of Business and Management, Bhopal (M.P.), India
Email: malhosiaajay@gmail.com

5Computer Science Engineering, Oriental Institute of Science and Technology, Bhopal, India
Email: joyvib@gmail.com


ABSTRACT

The convergence of machine learning and artificial intelligence with electronic health records and Internet of Things–based health monitoring has created a transformative paradigm for chronic disease prevention through predictive modeling and continuous patient surveillance. Chronic diseases impose a persistent burden on global healthcare systems due to their long latency periods, multimorbidity patterns, and the need for sustained clinical management. Traditional episodic care models are increasingly inadequate for early risk detection and proactive intervention. In this context, the integration of longitudinal clinical data from electronic health records with high-frequency physiological and behavioral data streams generated by connected sensing devices enables the development of dynamic, real-time risk prediction frameworks. These intelligent systems facilitate early identification of disease trajectories, personalized intervention strategies, and automated clinical decision support while improving healthcare accessibility and resource optimization. Advanced learning architectures, including deep temporal models, multimodal fusion techniques, and federated learning environments, support scalable and privacy-preserving analytics across distributed healthcare infrastructures. Continuous surveillance models further enable anomaly detection, deterioration forecasting, and adaptive care pathways for high-risk populations. The proposed research investigates the design of an interoperable predictive ecosystem that combines heterogeneous healthcare data sources, supports explainable clinical intelligence, and enhances preventive care delivery. The study also explores the implications of such systems for precision medicine, cost reduction, and improved patient outcomes. By shifting healthcare from reactive treatment to proactive prevention, AI-driven predictive surveillance frameworks offer a sustainable and patient-centric approach for managing chronic conditions in digitally connected healthcare environments.

Keywords: Machine learning, Artificial intelligence, Electronic health records, Internet of Things, Predictive healthcare, Chronic disease prevention.

How to cite this article: Murarka SK, Jain N, Sharma V, Malhosia A, Chaurasiya VK. ML and AI predictive modeling and continuous patient surveillance for chronic disease prevention using electronic health records and IoT-based data streams. Int J Drug Deliv Technol. 2026;16(8s): 90-96; DOI: 10.25258/ijddt.16.8s.17

Source of support: None.

Conflict of interest: None