Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jun 18, 2025
Open Peer Review Period: Jun 19, 2025 - Aug 14, 2025
Date Accepted: Nov 6, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited.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.
Effectiveness of AI-Enabled mHealth versus traditional mHealth for reducing diabetes risk behavior in Rural India: A quasi-experimental pre-post study
ABSTRACT
Background:
India faces high rates of diabetes and prediabetes, with traditional mobile health (mHealth) interventions showing promise in promoting healthy lifestyle changes.
Objective:
Therefore, we aimed to evaluate the effectiveness of an AI-enabled mHealth intervention compared to traditional mHealth in fostering diabetes prevention behaviors in rural district of Gulbarga, Karnataka, South India.
Methods:
A quasi-experimental pre-post study was conducted among adult without diabetes (n=1048) in Gulbarga. Participants were randomized into intervention and control groups. The control group received static diabetes prevention messages via WhatsApp, while the intervention group received customized messages twice a week based on individual feedback through reinforcement learning algorithms. Data was collected via home interviews on demographics, diabetes knowledge, and lifestyle behaviors. Multivariate logistic regression models evaluated the influence of various covariates on the likelihood of achieving positive outcomes and assessed changes over time within the AI-enabled mHealth group.
Results:
The AI group showed that participants engaged in regular exercise (66.7% to 72.8%, p=0.017) and the duration of physical activity (15.4% increase, p<0.001) was increased than non-AI group. The AI group showed a significant increase in performing household chores (93.5% to 98%, p=0.009), while no dietary habit changes were noted in either group. Age (26–35 years, aOR:2.4, p<0.001) in the non-AI group and baseline physical activity (>30 min/day, aOR:1.5, p=0.005) as predictors of reducing diabetes risk behaviours in both groups. BMI reductions were modest and non-significant, with a slight decrease in the AI group.
Conclusions:
AI-driven mHealth was more effective in promoting physical activity suggesting that integrating AI into mHealth strategies can enhance behavior change and enable scalable interventions in community settings.
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.