Researchers propose a new framework to evaluate and improve blood pressure estimation using photoplethysmography (PPG). They argue that current methods obscure model failures during rapid blood pressure fluctuations. Their approach identifies change points in blood pressure trajectories and evaluates performance specifically during these periods, revealing significant performance degradation in state-of-the-art models. To address this issue, they introduce a re-calibration framework triggered by detected change points, improving robustness without modifying model architectures. --- Why it matters: This matters because accurate continuous blood pressure monitoring is crucial for real-world applications, and current methods may not be reliable during rapid fluctuations. This work highlights the importance of fluctuation-aware evaluation and calibration in PPG-based blood pressure estimation. Source: https://arxiv.org/abs/2608.18639