Paperdoi:10.1093/sleep/zsag229
Prediction of cardiovascular outcomes using electrocardiography from overnight polysomnography
SLEEP (Oxford Academic), advance article; OUP page shows published 2026-10-09 (OpenAlex publicationdate 2026-09-04)
Licence: CC BY-NC (OpenAlex)
TL;DR
Deep residual network with attention, pretrained for arrhythmia detection, fine-tuned on single-lead PSG ECG + expert sleep stages from 15,809 MGH patients. Predicts 10-year AF, stroke, MI, HF and all-cause death; external validation on Emory (9,810) and BIDMC (12,576). Outcomes from ICD-9/10 codes.
- Form factor: clinical
Abstract
Study Objectives
Polysomnography (PSG) is the gold standard for diagnosing sleep disorders, which are recognized as cardiovascular risk factors. Single-lead electrocardiograms (ECGs) are recorded during PSG but rarely analyzed, presenting an opportunity to leverage overnight ECGs for cardiovascular risk prediction.
Materials and Methods
We applied a deep residual neural network with attention to single-lead ECGs from PSG, combined with sleep stage data, to predict 10-year risk of atrial fibrillation (AF), stroke, myocardial infarction (MI), heart failure (HF), and death. The network, trained for arrhythmia detection, was finetuned on 15 809 Massachusetts General Hospital patients. External validation used cohorts from Emory University Hospital (EUH) (n = 9810) and Beth Israel Deaconess Medical Center (BIDMC) (n = 12 576), with outcomes derived from electronic health records (ICD-9/10 codes).
Results
Cox proportional hazards models showed that neural-network output (NN-output) was strongly associated with long-term cardiovascular risk (p Conclusions
Deep learning applied to nocturnal ECGs with sleep stage information captures cardiac abnormalities, offering a tool for cardiovascular risk stratification. Integrating such prediction into PSG could enhance detection and support personalized clinical decision-making.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by-nc/4.0/
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
APA
Koscova, Z., Nasiri, S., Reyna, M. A., Bhatia, N. K., Rad, A. B., Sameni, R., Sun, H., Turley, N., Katwa, U., Hwang, D., Stone, K. L., Trotti, L. M., Thomas, R. J., Westover, M. B., & Clifford, G. D. (2026). Prediction of cardiovascular outcomes using electrocardiography from overnight polysomnography. SLEEP , advance article. https://doi.org/10.1093/sleep/zsag229
BibTeX
@article{koscova2026prediction,
title = {{Prediction of cardiovascular outcomes using electrocardiography from overnight polysomnography}},
author = {Koscova, Zuzana and Nasiri, Samaneh and Reyna, Matthew A. and Bhatia, Neal Kumar and Rad, Ali Bahrami and Sameni, Reza and Sun, Haoqi and Turley, Niels and Katwa, Umakanth and Hwang, Dennis and Stone, Katie L. and Trotti, Lynn Marie and Thomas, Robert Joseph and Westover, M. Brandon and Clifford, Gari D.},
year = {2026},
journal = {SLEEP , advance article},
doi = {10.1093/sleep/zsag229}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
