Currently submitted to: Journal of Medical Internet Research
Date Submitted: Jun 25, 2026
Open Peer Review Period: Jun 25, 2026 - Aug 20, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited.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.
Artificial Intelligence-Based Exercise Prescription for Chronic Disease Management An Umbrella Review of Systematic Reviews and Meta-Analyses
ABSTRACT
Background:
Background:
AI-based exercise prescription offers a new paradigm for chronic disease management, but the evidence base requires systematic synthesis.
Objective:
Objective:
To synthesize evidence from systematic reviews and meta-analyses on AI-driven exercise prescription for chronic diseases, and to assess methodological quality.
Methods:
Methods:
We searched PubMed, Embase, Web of Science, Cochrane Library, and IEEE Xplore up to December 2025. Systematic reviews evaluating AI-based exercise prescription in adults with chronic diseases were included. Methodological quality was assessed with AMSTAR-2, evidence certainty with GRADE, and study overlap with the corrected covered area index.
Results:
Results:
Eighteen reviews (312 primary studies, 97,648 participants) were included. AI-based exercise prescription significantly reduced HbA1c (WMD −0.58%, 95% CI −0.81 to −0.35), systolic blood pressure (WMD −5.23 mmHg, 95% CI −7.14 to −3.32), and improved cardiorespiratory fitness (SMD 0.47, 95% CI 0.29–0.65). AMSTAR-2 ratings: 4 high, 7 moderate, 5 low, 2 critically low. GRADE certainty was high for glycemic control, moderate for blood pressure and fitness.
Conclusions:
Conclusions:
AI-based exercise prescription provides clinically meaningful benefits across chronic diseases. Future priorities include algorithm standardization, larger trials, and safety monitoring.
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.