Real-Time Monitoring of Patient Adherence Using AI

Purpose: Patient compliance to prescribed therapies remains a persistent challenge in healthcare, particularly for chronic disease management. Non-adherence can lead to suboptimal treatment responses, increased hospitalizations, and higher healthcare expenditures. This study aims to develop an AI-based adherence monitoring framework that enables real-time tracking of patient behavior and medication intake, thereby improving compliance and health outcomes. Methodology: Experimental validation was conducted using real-world datasets. Findings: The AI-based adherence monitoring system demonstrated high predictive accuracy of up to 97.7% and improved patient adherence rates by 6.1%–32.7% compared to traditional monitoring approaches. The system’s real-time monitoring and predictive capabilities enable proactive interventions that enhance treatment outcomes. Unique Contribution to Theory, Practice, and Policy: This research advances the field by transforming adherence monitoring from a passive to a dynamic, patient-focused process. The framework contributes to theory by integrating AI and behavioral analytics in chronic disease management, supports clinical practice with scalable and secure real-time monitoring, and informs health policy by demonstrating cost-effective strategies for improving adherence and patient care.