Beyond Point-Wise Accuracy: Assessing Temporal Fidelity and Calibration Drift in PPG-Based Wearable Blood Pressure Estimation

Le résumé fourni par la source

Cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) provides a convenient and scalable alternative to traditional cuff-based measurements. While prior studies have predominantly emphasized point-wise accuracy, calibration stability and long-term trend estimation-crucial for practical wearable applications-remain less explored. In this paper, we present a cuffless BP estimation approach combining a 1D EfficientNet regressor with a ridge regression calibration layer (RidgeCalib). We evaluated this system on a dataset of 243 participants undergoing synchronized PPG and reference BP monitoring over 24 hours. Our results indicate that the proposed framework effectively tracks general BP trends and that RidgeCalib significantly reduces prediction errors compared to the uncalibrated baseline. Despite these improvements, calibration drift still occurred over time, highlighting the limitations of single-point calibration methods. Overall, our findings underscore the potential of single-site PPG for continuous BP monitoring, while emphasizing the need for adaptive calibration strategies to further enhance reliability.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.