Wearable-derived REM sleep as a modifiable risk factor for cardiovascular disease: A multimodal prediction model in the All of Us Research Program

Jiseung Kang

doi:10.1016/j.pcad.2026.03.002

Wearable-derived REM sleep as a modifiable risk factor for cardiovascular disease: A multimodal prediction model in the All of Us Research Program

2026-03-04

0

PRE

AI

J

Jiseung Kang

H

Hyeon Jin Kim

Y

Yesol Yim

M

Min Seo Kim

J

Jaeyu Park

Y

Yejun Son

G

Guillaume Fond

L

Laurent Boyer

D

Dong Keon Yon *

C

Christa J. Nehs *

DOI：10.1016/j.pcad.2026.03.002

Original

Original request for help

Save

Abstract

En 中文

• Short and long sleep duration were associated with a higher risk of incident cardiovascular diseases (CVDs), showing a U-shaped relationship. • Reduced REM sleep (<20%) was consistently linked to increased risk of CVD. • Two multimodal prediction strategies (non-invasive and invasive) were developed for CVD prediction and showed superior performance to established conventional cardiovascular risk scores. • Integrating objective sleep-stage measures and multimodal digital health data into future cardiovascular prevention strategies and guideline development.

Keywords:

REM sleep

cardiovascular disease

wearable devices

multimodal prediction

sleep duration

Wearable-derived REM sleep as a modifiable risk factor for cardiovascular disease: A multimodal prediction model in the All of Us Research Program

Abstract

Journal

Organization

Cited Papers

Citing Papers