Foundation models enable wearable signal screening for cardiovascular disease among people living with HIV
Open Access
- 16 January 2026
- journal article
- research article
- Published by Springer Nature in Communications Medicine
- Vol. 6 (1)
Abstract
Background: Cardiovascular disease screening faces significant challenges in resource-limited settings, where infrastructure and computational constraints preclude advanced assessment. These constraints are particularly acute for people living with human immunodeficiency virus (HIV), who experience elevated cardiovascular risk yet often receive care in clinics without specialist diagnostic capacity. Pretrained physiological foundation models offer potential for low-cost screening using wearable sensors, though their applicability in resource-constrained settings remains unclear. Methods: We evaluate pretrained physiological embeddings from foundation models for cardiovascular disease detection using photoplethysmography signals from 80 people living with HIV in Ho Chi Minh City, Vietnam. Of 80 participants, 13 (16%) had cardiologist-confirmed cardiovascular disease. We compare strictly zero-shot deployment (NormWear without local training) with frozen PaPaGei embeddings plus locally trained classifier, alongside traditional approaches. Results: Here we show that the PaPaGei-embedding approach achieves area under the receiver operating characteristic curve 0.769 (95% confidence interval: 0.70, 0.84) and average precision 0.489 (0.37, 0.61) in this pilot cohort, numerically higher than zero-shot NormWear (0.610; 0.226), principal component analysis features (0.651; 0.208), and supervised clinical models (0.744; 0.433). This approach requires local labels for classifier training but avoids computationally intensive foundation model fine-tuning. However, given the small positive class size (13 cases), these findings require validation in larger cohorts. PaPaGei embeddings capture clinically coherent structure: patients on dolutegravir-based regimens cluster in low-risk regions, while those with high cholesterol variability occupy high-risk areas. Conclusions: These preliminary findings provide a potential methodological framework for deploying foundation models in resource-constrained settings, though adequately powered, multi-centre validation is essential before clinical implementation.Keywords
Funding Information
- EPSRC CDT Health Data Science
- Royal Academy of Engineering
This publication has 35 references indexed in Scilit:
- The importance of resource awareness in artificial intelligence for healthcareNature Machine Intelligence, 2023
- Performance of Cardiovascular Risk Prediction Models Among People Living With HIVJAMA Cardiology, 2023
- Associations between integrase strand-transfer inhibitors and cardiovascular disease in people living with HIV: a multicentre prospective study from the RESPOND cohort consortiumThe Lancet HIV, 2022
- AI in health and medicineNature Medicine, 2022
- Ethical limitations of algorithmic fairness solutions in health care machine learningThe Lancet Digital Health, 2020
- The importance of interpretability and visualization in machine learning for applications in medicine and health careNeural Computing and Applications, 2019
- Artificial Intelligence in CardiologyJACC, 2018
- HIV Infection and the Risk of Acute Myocardial InfarctionJAMA Internal Medicine, 2013
- Preventing CVD in resource-poor areas: perspectives from the 'real-world'Nature Reviews Cardiology, 2009
- Decreased heart rate variability and its association with increased mortality after acute myocardial infarctionThe American Journal of Cardiology, 1987