19 November 2025 in Communications Medicine
Photoplethysmography (PPG), increasingly available through wearable devices, provides a non-invasive means of monitoring human hemodynamics. In this study, we introduce artificial intelligence-derived photoplethysmography (AI-PPG) age, a deep learning-based estimate of biological age from raw PPG signals, and evaluate its potential as a digital biomarker for cardiovascular health. We developed a deep learning model with a distribution-aware loss function to reduce bias from imbalanced data. The model was trained and evaluated on the UK Biobank cohort (N = 212,231). We analyzed the association between the AI-PPG age gap (AI-PPG age minus calendar age) and multiple cardiovascular and metabolic outcomes, assessed its longitudinal value using serial PPG measurements, and externally validated its generalizability in an independent MIMIC-III-derived cohort (N = 2343). After adjusting for key confounders, participants with an AI-PPG age gap greater than 9 years have a significantly higher risk of major adverse cardiovascular and cerebrovascular events (hazard ratio of 2.37, p = 8.46 × 10-80), as well as seven secondary outcomes including coronary heart disease and myocardial infarction (all p < 0.005). Conversely, those with a gap below -9 years show a lower risk profile. Longitudinal analysis demonstrates that changes in AI-PPG age add predictive value over time. In the external validation cohort, each one-year increase in AI-PPG age gap is associated with higher in-hospital mortality (odds ratio of 1.02, p = 0.01). AI-PPG age is a scalable, non-invasive biomarker for cardiovascular health assessment. Integrated with wearable devices, it may enable population-level screening, personalized monitoring, and early intervention.
1 January 2026 in Health Data Science
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.