Currently submitted to: JMIR mHealth and uHealth
Date Submitted: Jul 30, 2026
Open Peer Review Period: Jul 31, 2026 - Sep 25, 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Warning: This is an author submission that is not peer-reviewed or edited.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.
Serial Digital Six-Minute Walk Test Features for Predicting 90-Day Improvement in Left Ventricular Ejection Fraction During Cardiac Rehabilitation: Cohort Study
ABSTRACT
Background:
Improvement in left ventricular ejection fraction (LVEF) is an important marker of treatment response and functional recovery in heart failure. Conventional six-minute walk test (6MWT) assessment relies mainly on six-minute walk distance (6MWD) and does not characterize physiological responses during walking and recovery.
Objective:
We evaluated whether physiological and recovery features derived from baseline and 45-day digital 6MWTs, together with their between-test changes, enhanced prediction of 90-day LVEF improvement beyond clinical variables and conventional 6MWD.
Methods:
This cohort study used prospectively collected data in a retrospective modeling analysis. Participants with valid baseline and 90-day LVEF measurements, a baseline 6MWT, and a second 6MWT performed 45 ± 15 days later were included. The primary endpoint was an LVEF increase of ≥3 percentage points. L2-regularized logistic regression compared clinical, single-test, and serial digital 6MWT feature sets. Performance was assessed using subject-level five-fold cross-validation, repeated validation across random seeds, calibration analysis, and decision curve analysis.
Results:
Among 43 participants, 20 met the LVEF-improvement endpoint and 23 did not. Neither baseline nor repeated 6MWD differed significantly between groups. Models using continuous features from the first or repeated 6MWT yielded AUROCs of 0.608 ± 0.057 and 0.703 ± 0.017, respectively. The clinical-variable model achieved an AUROC of 0.777 ± 0.034, which increased to 0.875 ± 0.012 after adding first-test continuous features. The full serial model combining clinical variables, both 6MWTs, and between-test changes achieved the highest AUROC of 0.910 ± 0.014.
Conclusions:
Serial digital 6MWT features improved discrimination of 90-day LVEF improvement beyond clinical variables and conventional 6MWD-based assessment, supporting their potential value for mid-rehabilitation evaluation. Clinical Trial: Chinese Clinical Trial Registry, ChiCTR2400085254. Retrospectively registered on 4 June 2024.
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.