Currently submitted to: JMIR mHealth and uHealth
Date Submitted: Apr 17, 2026
Open Peer Review Period: Apr 29, 2026 - Jun 24, 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Warning: This is an author submission that is not peer-reviewed or edited.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.
Can machine learning-driven goal setting increase physical activity? A cohort analytic study of 1,249 North American mHealth app users.
ABSTRACT
Background:
Insufficient physical activity (PA) is a global pandemic associated with the development of noncommunicable diseases.
Objective:
To examine whether an mHealth PA intervention with financial incentives (FI) is improved with the incorporation of a machine learning (ML)-driven goal setting algorithm.
Methods:
A 17-week cohort analytic study was conducted among users of the Telus Wellbeing corporate wellness app, an mHealth PA intervention with FI targeting North American employees (March-June 2022). A five-week baseline period was followed by a 12-week intervention, during which users were randomized (1:2) into either (a) static goal (control), or (b) adaptive, ML-driven goal (intervention) groups. A linear mixed model (LMM) analyses compared baseline to Week 12 and was conducted to examine change in primary and secondary outcomes over the intervention period (p<0.05). Estimated marginal means (EMM) were reported across four time points (baseline, Week 4, Week 8, and Week 12).
Results:
A total of 1,249 participants (control: n=447; intervention: n=802) were included (59.6% 30-to-50 years old; 48.8% women; baseline steps: 6,313/day). LMM analyses suggest the overall weekly mean daily step count trend increased from baseline to Week 12 for the entire sample (i.e., mean difference [95% CI]: 607 [96-1118] steps/day; d=0.07; p=0.022). Regarding the primary study objective, groups did not differ significantly on weekly mean daily step count change from baseline to Week 12 (i.e., mean difference [95% CI]: 19 [-768-806] steps/day; d=0.001; p=0.960).
Conclusions:
The Telus Wellbeing app increased mean daily step count over a 12-week period. A supervised ML-driven goal setting algorithm did not boost PA or app engagement, compared to static goal setting over 12 weeks. Future research should test refined ML-driven approaches with more diverse study samples that may better boost PA with mHealth intervention. Clinical Trial: This study was pre-registered at ClinicalTrials (NCT06388317), received institutional ethical approval and was conducted following the STROBE guidelines for cohort studies.
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.