Automated loss of pulse detection on a consumer smartwatch

Out-of-hospital cardiac arrest is a time-sensitive emergency that requires prompt identification and intervention: sudden, unwitnessed cardiac arrest is nearly unsurvivable<sup>1-3</sup>. A cardinal sign of cardiac arrest is sudden loss of pulse<sup>4</sup>. Automated biosensor detection of unwitnessed cardiac arrest, and dispatch of medical assistance, may improve survivability given the substantial prognostic role of time<sup>3,5</sup>, but only if the false-positive burden on public emergency medical systems is minimized<sup>5-7</sup>. Here we show that a multimodal, machine learning-based algorithm on a smartwatch can reach performance thresholds making it deployable at a societal scale. First, using photoplethysmography, we show that wearable photoplethysmography measurements of peripheral pulselessness (induced through an arterial occlusion model) manifest similarly to pulselessness caused by a common cardiac arrest arrhythmia, ventricular fibrillation. On the basis of the similarity of the photoplethysmography signal (from ventricular fibrillation or arterial occlusion), we developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and free-living conditions. Following its development, we evaluated the end-to-end algorithm prospectively: there was 1 unintentional emergency call per 21.67 user-years across two prospective studies; the sensitivity was 67.23% (95% confidence interval of 64.32% to 70.05%) in a prospective arterial occlusion cardiac arrest simulation model. These results indicate an opportunity, deployable at scale, for wearable-based detection of sudden loss of pulse while minimizing societal costs of excess false detections<sup>7</sup>.

Authors

Institutions

Publication Details

Journal
Nature
Published
2025-02-26
DOI
https://doi.org/10.1038/s41586-025-08810-9
Citations
25
Primary Topic
Power Line Communications and Noise
Type
article
Field-Weighted Citation Impact
18.26
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Automated loss of pulse detection on a consumer smartwatch

Jack Phan, Yun-Ling Lee, Martin Wimmer, Tajinder Gadh et al.
25 citations
Nature
Power Line Communications and Noise
18.26
article

Automated loss of pulse detection on a consumer smartwatch

Jack Phan, Yun-Ling Lee, Martin Wimmer, Tajinder Gadh, Anupam Pathak, Pushmeet Kohli, Bakul Patel, E. L. Shi, E. Silver, S. Rajagopalan, Ling Cai, Thanh G. Phan, Shelten Yuen, Shwetak Patel, Alistair Connell, A Vasquez, Kamal Shah, Thomas D. Rea, Jacqueline Baras Shreibati, Jacob E. Sunshine, Shakuntala Chhabra, David P Miller, Yiwen Chen, Anran Wang, Daniel McDuff, Mark Malhotra, Cary Fox, Jim Taylor, Beszel Hawkins, Dinesh Puppala, Pramod Rudrapatna, Marc Stogaitis, Jitender Munjal, Anthony Stange, Enxun Wei, Tracy Giest
article en
25 citations

Abstract

Out-of-hospital cardiac arrest is a time-sensitive emergency that requires prompt identification and intervention: sudden, unwitnessed cardiac arrest is nearly unsurvivable<sup>1-3</sup>. A cardinal sign of cardiac arrest is sudden loss of pulse<sup>4</sup>. Automated biosensor detection of unwitnessed cardiac arrest, and dispatch of medical assistance, may improve survivability given the substantial prognostic role of time<sup>3,5</sup>, but only if the false-positive burden on public emergency medical systems is minimized<sup>5-7</sup>. Here we show that a multimodal, machine learning-based algorithm on a smartwatch can reach performance thresholds making it deployable at a societal scale. First, using photoplethysmography, we show that wearable photoplethysmography measurements of peripheral pulselessness (induced through an arterial occlusion model) manifest similarly to pulselessness caused by a common cardiac arrest arrhythmia, ventricular fibrillation. On the basis of the similarity of the photoplethysmography signal (from ventricular fibrillation or arterial occlusion), we developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and free-living conditions. Following its development, we evaluated the end-to-end algorithm prospectively: there was 1 unintentional emergency call per 21.67 user-years across two prospective studies; the sensitivity was 67.23% (95% confidence interval of 64.32% to 70.05%) in a prospective arterial occlusion cardiac arrest simulation model. These results indicate an opportunity, deployable at scale, for wearable-based detection of sudden loss of pulse while minimizing societal costs of excess false detections<sup>7</sup>.

NatureVol. 642(8066)
Google (United States) (US), Public Health – Seattle & King County (US), University of Washington (US), Arizona Heart Hospital (US), Cancer Research And Biostatistics (US), Google (United Kingdom) (GB), Baylor Jack and Jane Hamilton Heart and Vascular Hospital (US)
Affordable and clean energy
Openalex Percentile: Top 1%
Power Line Communications and Noise
18.26
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.