A Scoping Review of Deep Learning Methods for Photoplethysmography Data

Background: Photoplethysmography (PPG) is a noninvasive optical sensing technique widely used to capture hemodynamic information, with broad deployment in both clinical monitoring systems and wearable devices. In recent years, the integration of deep learning has substantially advanced PPG signal analysis and expanded its applications across healthcare and nonhealthcare domains. Methods: We conducted a comprehensive literature search for studies applying deep learning to PPG data published between 2017 January 1 and 2025 December 31, using Google Scholar, PubMed, and Dimensions. The included studies were analyzed from 3 key perspectives: tasks, models, and data. Results: A total of 460 papers applying deep learning techniques to PPG signal analysis were included. These studies span a wide range of application domains, from traditional physiological monitoring tasks such as cardiovascular assessment to emerging applications including sleep analysis, cross-modality signal reconstruction, and biometric identification. Conclusions: Deep learning has substantially advanced PPG signal analysis by enabling more effective extraction of physiological information. Compared with traditional machine learning approaches reliant on handcrafted features, deep learning methods generally achieve improved performance and offer greater flexibility in model development. Nevertheless, several challenges remain, including limited availability of large-scale high-quality datasets, insufficient validation in real-world environments, and concerns over model interpretability, scalability, and computational efficiency. Addressing these challenges and exploring emerging research directions will be essential for further progress in deep learning-based PPG analysis.