GRP-20219 Continuous Monitoring of Cardiovascular Risk From Smartwatch Data Using a Knowledge Distillation Framework

GRP-20219 Continuous Monitoring of Cardiovascular Risk From Smartwatch Data Using a Knowledge Distillation Framework

https://www.kennesaw.edu/ccse/events/computing-showcase/fa25-cday-program.php

Cardiovascular Disease (CVD) is one of the leading causes of global health concern, but current risk assessments are limited to episodic clinical visits. Most machine learning (ML) models trained on clinical data offer high accuracy but are not practical for continuous monitoring. Smartwatch-based wearables provide continuous real-time physiological data but lack clinical validation for robust risk prediction outside the clinical setting. To bridge this gap, we proposed a novel teacher-student knowledge distillation framework that transfers knowledge of complex and large EHR datasets to a small Fitbit smartwatch dataset-based prediction model. The student model achieves promising accuracy, identifying all types of derived CVD risk profile groups. Feature importance analysis revealed that daily average steps and sedentary time are the most prominent wearable-derived CVD risk predictors. Our study introduces a non-invasive continuous health monitoring framework, demonstrating that passively collected daily metrics can be transformed to clinically powerful early warnings of an individual’s long-term cardiovascular health plan.