Cardiac condition monitoring through photoplethysmogram signal denoising using wearables: Can we detect coronary artery disease with higher performance efficacy?

Abstract

For affordable cardiac health monitoring, it is required to ensure accurate cardiac condition detection from smartphone or wearable-extracted photoplethysmogram (PPG) signals through precise identification, and removal of signal corruption. Presence of noise particularly due to motion artifacts strongly impacts the outcome of analysis. We establish that denoising of PPG signal would pave ways for better clinical prediction than analyzing the signal in presence of noise. In this paper, we prove that analyzing on cleaned (denoised) PPG signal yields significant performance efficacy improvement while performing Coronary Artery Disease (CAD) identification. The proposed method is independent on the clinical analytics and CAD detection is considered to be a use case to justify our claim that physiological signal pre-processing, specifically denoising can substantially improve the overall performance effectiveness and clinical utility.