Adaptive Human Digital Twin for Personalized Health Monitoring using Machine Learning

Adaptive Human Digital Twin system integrates machine learning techniques with personalized healthcare monitoring. The system utilizes user inputs such as sleep patterns, stress levels, and physical activity to build a digital representation of an individual. It performs baseline calibration, risk score fusion, and intervention planning to provide actionable health insights. Experimental results demonstrate that Random Forest outperforms Linear Regression in prediction accuracy. The system enables continuous monitoring, adaptive learning, and personalized recommendations for improved health management.