Wearable devices have the potential to support continuous physiological monitoring in both clinical and home settings. Although photoplethysmography (PPG) enables comfortable long-term monitoring, it does not directly provide electrocardiographic (ECG) information. This study aims to establish a synchronized dataset of ECG and PPG recordings that can be used to develop and evaluate artificial intelligence algorithms for reconstructing ECG parameters, particularly QT/QTc, from PPG signals.
Approximately 50 healthy adult volunteers will be enrolled in this single-center, single-arm observational feasibility study. Participants will wear the Corsano CardioWatch 287-2 together with a reference continuous ECG device for approximately 24 hours. During the study, synchronized recordings will be collected during standardized activities (rest, standing, and light walking) as well as during normal daily activities.
The primary endpoints include completeness of paired ECG-PPG recordings, synchronization quality, and the proportion of recordings suitable for QT/QTc annotation. Secondary endpoints include participant comfort and usability of the wearable monitoring system, together with technical performance measures such as signal quality, device connectivity, and data completeness.
The resulting dataset will support future development and validation of AI-based methods for ECG parameter reconstruction from wearable PPG signals.