Deep Learning Advances in Photoplethysmography Signal Analysis
A scoping review published on arXiv (2401.12783v3) examines deep learning methods applied to photoplethysmography (PPG) data. PPG is a non-invasive optical sensing technique used for capturing hemodynamic information in clinical monitoring and wearable devices. The review covers studies from January 1, 2017 to December 31, 2025, sourced from Google Scholar, PubMed, and Dimensions. It analyzes 460 papers from three perspectives: tasks, models, and data. Applications range from traditional physiological monitoring like cardiovascular assessment to emerging uses in non-healthcare domains.
Key facts
- arXiv:2401.12783v3 is a scoping review of deep learning for PPG data.
- PPG is a non-invasive optical sensing technique for hemodynamic information.
- Literature search covered January 1, 2017 to December 31, 2025.
- Sources used: Google Scholar, PubMed, and Dimensions.
- 460 papers applying deep learning to PPG were included.
- Analysis focused on tasks, models, and data.
- Applications include cardiovascular assessment and emerging non-healthcare uses.
- Deep learning has advanced PPG signal analysis and expanded its applications.
Entities
Institutions
- arXiv
- Google Scholar
- PubMed
- Dimensions