Artificial Intelligence-Enabled Mobile Health Intervention (mDiabetes) to Reduce Diabetes Risk Behaviors in Rural...

Area of Science:

• Public Health
• Digital Health
• Behavioral Science

Background:

• India faces a significant dual burden of diabetes and prediabetes.
• Existing mobile health (mHealth) interventions often use generic messages, failing to address individual behavioral patterns and needs.

Purpose of the Study:

• To evaluate the effectiveness of an AI-enabled personalized mHealth intervention (mDiabetes) versus traditional non-personalized mHealth messaging.
• To promote diabetes risk reduction behaviors among adults in rural South India.

Main Methods:

• A quasi-experimental pre-post study involving 1048 adults without diabetes.
• Intervention group received customized messages via WhatsApp; control group received static messages.
• Data collected via home interviews; analyzed using chi-square, t-tests, logistic regression, and ANCOVA.

Main Results:

• No significant between-group differences in primary outcomes at 6-month follow-up.
• Both groups showed similar odds of meeting physical activity goals.
• Factors like baseline activity, age, and employment influenced physical activity and fruit intake.

Conclusions:

• AI-enabled and traditional mHealth interventions demonstrate comparable effectiveness for diabetes prevention in rural India.
• Simple, well-designed mHealth interventions on accessible platforms like WhatsApp can drive behavior change.
• This suggests potential for scalable, cost-effective, and equitable diabetes prevention in resource-limited settings.