Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
Here the authors show that applying artificial intelligence (AI) to multimodal waveforms (photoplethysmography and accelerometry) recorded using a widely available consumer smartwatch (AI-PPG-ACC-HTN), without any cuff calibration, can detect hypertension with accuracy levels comparable to traditional cuffed blood pressure (BP) devices in the existing clinical framework. The authors validated AI-PPG-ACC-HTN in a prospective, multicenter study of 196 diverse participants free from known cardiovascular disease and antihypertensive medication against gold-standard 24-hour ambulatory BP monitoring. Over seven days of real-world monitoring, AI-PPG-ACC-HTN detected hypertension with a sensitivity of 65.8% (95% CI, 54.0%-76.3%), specificity of 90.0% (95% CI, 83.2%-94.7%), and positive predictive value (PPV) of 80.6% (95% CI, 68.6%-89.6%).
Published
Nature, 2026
Signals
PPG, IMU
Year
2025
Result
Over seven days of real-world monitoring, AI-PPG-ACC-HTN detected hypertension with a sensitivity of 65.8% (95% CI, 54.0%-76.3%), specificity of 90.0% (95% CI, 83.2%-94.7%), and positive predictive value (PPV) of 80.6% (95% CI, 68.6%-89.6%).
Result
In comparison, initial office BP screening achieved a sensitivity of 55.3% (95% CI, 43.4%-66.7%), specificity of 90.0% (95% CI, 83.2%-94.7%) and PPV of 77.8% (95% CI, 64.4%-88.0%).
Cite the publication recorded for this model. Check it against the publisher before submitting.
Di Achille, P., Cai, L., Wu, J., Gao, M., Daryani, B., Wang, J., Khanna, U., Ko, H., Pathak, A., Malhotra, M., Patel, S., Shreibati, J. B., Juraschek, S. P., Rudrapatna, P., Thompson, M., & Poh, M.-Z. (2025). Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026). Nature. https://doi.org/10.1038/s41586-026-11336-3
Di Achille, Paolo, Lawrence Cai, Jiang Wu, Mingwu Gao, Bhavna Daryani, Jonathan Wang, and Utkarsh Khanna, et al. 2025. "Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026)." Nature. https://doi.org/10.1038/s41586-026-11336-3.
Di Achille, P., Cai, L., Wu, J., Gao, M., Daryani, B., Wang, J. and Khanna, U. et al. (2025) 'Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026)', Nature. doi: 10.1038/s41586-026-11336-3.
Di Achille, Paolo, et al. "Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026)." Nature, 2025. https://doi.org/10.1038/s41586-026-11336-3.
P. Di Achille et al., "Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026)," Nature, 2025, doi: 10.1038/s41586-026-11336-3.
@article{achille2025opportunistically,
title = {{Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch (AI-PPG-ACC-HTN; Di Achille, Poh et al., Nature 2026)}},
author = {Di Achille, Paolo and Cai, Lawrence and Wu, Jiang and Gao, Mingwu and Daryani, Bhavna and Wang, Jonathan and Khanna, Utkarsh and Ko, Ho and Pathak, Anupam and Malhotra, Mark and Patel, Shwetak and Shreibati, Jacqueline B. and Juraschek, Stephen P. and Rudrapatna, Pramod and Thompson, Matthew and Poh, Ming-Zher},
year = {2025},
journal = {Nature},
doi = {10.1038/s41586-026-11336-3}
}
History
Added to the ChatPPG research hub
Newsletter
Get new PPG datasets, papers and models
Get alerts when AI-PPG-ACC-HTN (Google Waveform Encoder + HTN probe) is benchmarked on new datasets, plus the weekly digest.
New datasets, papers and models
Practical guides from the hub
Unsubscribe anytime
The waveform is an illustration of a PPG pulse, not a recording.
