Key result
State-space modeling of PPG signals enables robust continuous HRV monitoring using common wearable sensors.
Why the study?
Deriving reliable heart rate variability from photoplethysmography is highly difficult due to motion artifacts and pulse arrival time variability.
A novel multimodal state-space modeling framework significantly improves the accuracy of continuous heart rate variability estimation from wearable PPG sensors by mitigating motion artifacts.
Answers are grounded in this paper and cite their sources.
Supports continuous wearable HRV in real-world clinical settings; extends prior lab-based PPG methods to ambulatory cardiovascular research.
OBJECTIVE: 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). METHODS: 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. RESULTS: 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. CONCLUSION: Uncertainty-aware multimodal observations with an adaptive state-space model (SSM) yields robust HRV estimation under real-world artifacts. SIGNIFICANCE: 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.
No takes yet. Share an insight, caveat, or question.
Demirel et al. (2026) studied this question. Multimodal framework with an adaptive state-space model vs. Traditional peak detection and prior work was evaluated on Inter-beat interval accuracy and HRV indices (e.g., SDNN) (up to 80% error reduction). An adaptive state-space model using multimodal observations reduced SDNN estimation error by up to 80% relative to traditional peak detection across three public datasets.
Synapse has enriched 10 related papers. Consider them for comparative context: