Continuous Heart Rate Variability Estimation From PPG via State-Space Modeling

Heart rate variability (HRV) reflects autonomic regulation and is widely used in cardiovascular monitoring. Photoplethysmography (PPG) is commonly used for continuous heart rate (HR) tracking in daily life, but deriving reliable HRV from PPG is highly difficult because of motion artifacts and drift effects from variability in pulse arrival time (PAT).

We propose a multimodal framework that combines encoders for PPG, inertial measurements, and temperature signals with a learnable state-space model for inter-beat inference. The state-space dynamics adapt to non-linear changes and PAT-related shifts. A composite trust gate uses predicted uncertainty to down-weight corrupted intervals.

Using a single model configuration across three public datasets (DaLiA, WildPPG, BIDMC), our method consistently improves inter-beat interval accuracy and HRV indices compared to prior work. For SDNN, we reduce error by up to 80% relative to traditional peak detection, while improving agreement with ECG-derived references.

Uncertainty-aware multimodal observations with an adaptive state-space model (SSM) yields robust HRV estimation under real-world artifacts.

Our method enables robust HRV monitoring in realistic settings from common wearable sensors and provides strong baselines and results to support research and future applications.