Currently accepted at: JMIR Medical Informatics
Date Submitted: Mar 24, 2026
Date Accepted: Nov 12, 2026
This paper has been accepted and is currently in production.
It will appear shortly on 10.2196/95960
The final accepted version (not copyedited yet) is in this tab.
A Rule-Based Decision Support System for Safe and Personalized Exercise Prescription in Cardiac Rehabilitation : Development and Usability Study
ABSTRACT
Background:
Exercise-based cardiac rehabilitation (CR) is a class A recommendation for patients with cardiovascular disease. While exercise prescription is well supported during center-based rehabilitation, long-term exercise management during Phase III CR remains difficult to deliver, since this phase requires repeated, individualized adaptation of exercise programs. Existing digital tools focus mainly on initial exercise prescription while decision support for week-by-week adaptation of programs within guideline-based limits is still limited.
Objective:
The specific aim of this study was to develop a rule-based decision support system, the Rule-Based Exercise Prescription Tool (REPT), designed to provide end-to-end, guideline-based exercise prescription and progression support for CR patients, and to evaluate clinicians’ perceived safety, feasibility, and acceptability of the system in a simulation-based setting.
Methods:
REPT integrates guideline-based exercise goal assessment with weekly exercise prescription and progression. Recommendations were formalized as transparent, traceable rules using a conservative safety-first conflict resolution strategy and were coded into a machine-readable knowledge base. Appropriateness and feasibility were evaluated in a simulation-based design. In Phase 1, experts (n=3) tested 12 simulated patient cases; in Phase 2, general practitioners (n=33) externally evaluated predefined progression scenarios. Outcomes included perceived guideline compliance, safety, usefulness, feasibility, and acceptability.
Results:
We encoded 112 actionable rules and a weekly progression algorithm. In Phase 1, clinicians rated 92% of the generated exercise permissibility reports and initial exercise programs as safe and guideline consistent. In Phase 2, general practitioners accepted 79% (95% CI 72–87%) of the weekly exercise prescriptions and progression scenarios generated for the simulated case without modification, requested minor adjustments in 19%, and rejected 2%. More than 90% of clinicians rated the system as useful or very useful for decision support and education.
Conclusions:
In this simulation-based evaluation, clinicians perceived the developed solution as a feasible and acceptable end-to-end decision support framework for exercise prescription in CR, supporting structured, supervised exercise management over time. Further real-world evaluation is needed to assess usability in routine practice and clinical impact.
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.