The development of multi-sensor biomarkers offers a promising avenue for enhancing personalized healthcare and remote monitoring. This study focuses on the integration of accelerometer and electrocardiogram (ECG) data to create a comprehensive multi-sensor biomarker capable of assessing both physical activity and cardiovascular health. Accelerometers track movement patterns, activity levels, and postures, while ECG sensors monitor heart rate, heart rate variability (HRV), and overall cardiac function. By combining these data streams, it is possible to correlate physical exertion with heart performance, resulting in a more holistic health assessment. This research employs advanced machine learning algorithms to analyze synchronized accelerometer and ECG data, identifying patterns that reflect an individual's physiological state. The primary goal is to develop a reliable, real-time biomarker that can detect early signs of disease, monitor chronic conditions, and support preventive health measures. This multi-sensor approach aims to improve accuracy in health assessments by providing deeper insights into the relationship between physical activity and cardiovascular function.
Read full abstract