Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
This work addresses the need for clinically interpretable and hardware-informative PPG models in smart wearables, representing an incremental advancement over existing deep learning approaches.
The authors tackled the problem of extracting interpretable physiological parameters from photoplethysmography (PPG) signals by introducing PPGen, a biophysical model, and hybrid amortized inference (HAI) for fast and robust estimation, achieving accurate inference in in-silico experiments under diverse noise and sensor conditions.
Smart wearables enable continuous tracking of established biomarkers such as heart rate, heart rate variability, and blood oxygen saturation via photoplethysmography (PPG). Beyond these metrics, PPG waveforms contain richer physiological information, as recent deep learning (DL) studies demonstrate. However, DL models often rely on features with unclear physiological meaning, creating a tension between predictive power, clinical interpretability, and sensor design. We address this gap by introducing PPGen, a biophysical model that relates PPG signals to interpretable physiological and optical parameters. Building on PPGen, we propose hybrid amortized inference (HAI), enabling fast, robust, and scalable estimation of relevant physiological parameters from PPG signals while correcting for model misspecification. In extensive in-silico experiments, we show that HAI can accurately infer physiological parameters under diverse noise and sensor conditions. Our results illustrate a path toward PPG models that retain the fidelity needed for DL-based features while supporting clinical interpretation and informed hardware design.