Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Nov 27, 2024
Date Accepted: May 15, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Detection and analysis of circadian biomarkers for metabolic syndrome using wearable data and explainable artificial intelligence
ABSTRACT
Background:
Digital biomarker detection using wearable devices is utilized as a solution for managing metabolic syndrome (MetS) in daily life.
Objective:
This study aimed to detect digital biomarkers based on sleep and circadian rhythm using step counts and heart rate data obtained from wearable devices and to analyze important biomarkers for MetS risk groups.
Methods:
Circadian rhythm markers based on heart rate and step counts were analyzed, including the newly proposed continuous wavelet circadian rhythm energy. The detected markers were analyzed for their contribution to MetS using SHapley Additive exPlanations, Explainable Boosting Machine, and Tabular Neural Network models.
Results:
Analysis of sleep and circadian rhythm biomarkers using statistical analysis and artificial intelligence methods revealed that circadian rhythm markers were more important for MetS than sleep markers. Among circadian rhythm markers, heart rate-based markers were found to be more important than step counts. The continuous wavelet circadian energy proposed in this study showed the highest contribution to MetS in the artificial intelligence analysis results.
Conclusions:
The risk of MetS can be continuously identified and monitored in daily life by utilizing circadian rhythm markers.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.