Greedy-optimized Approach for Interbeat Interval and Heart Rate Variability Daily Monitoring using Wearable PPG

Abstract: Continuous monitoring of heart rate variability (HRV) provides insights in cardiovascular health. Wearable Photoplethysmography (PPG) assures convenient measurement of HRV. PPG, however, is susceptible to motion artifacts, considerably deteriorating the accuracy in estimation. In this study, a greedy-optimized approach is proposed for attaining high accuracy of interbeat intervals (IBIs) estimation from PPG signals collected during intensive daily activities. Utilizing the fact of continuity in heartbeats, the IBI estimation is converted into the shortest path problem in a directed acyclic graph, where candidate heartbeats from motion-contaminated PPG are regarded as vertices. The approach exploits a convex penalty function to optimize weight assignment in the shortest path calculation and a greedy fusion method to strengthen the selection process of optimal IBIs. Results achieve correlation of 0.96 for IBI estimation with the improvement of 58.4% in percentage error on the single-channel PPG signal from 2015 IEEE Signal Processing Cup. It also achieves correlation of 0.98 with percentage error of 2.2% in the two-channel PPG signal. Estimated and true HRV parameters are highly correlated. The approach is further validated on the PPG-DaLiA dataset with high correlation and low percentage error for IBI and HRV estimation in two daily activities, indicating the robustness of the proposed technique.