Effect of a Personalized Mobile Health Intervention Using Artificial Intelligence (the WARIFA App) Versus a Nonpersonalized Intervention on User-Defined Objectives, Healthy Lifestyles, and Management of Type 1 Diabetes (T1D): Protocol for a Randomized Controlled Trial

Clinical Snapshot

Key Findings

• P Value: Not yet available

• Effect Size: Not yet available - results pending publication

• Primary Outcome: Self-defined goal achievement measured on Likert scale 1-10

• Nnt Or Sensitivity: Cannot be calculated - results not published

• Confidence Interval: Not yet available

Clinical Application

Requires smartphone access and digital literacy, may face implementation challenges in resource-limited settings Relevant to Australian digital health initiatives and diabetes management programs, though app would need TGA evaluation for therapeutic claims Adults with type 1 diabetes and general population seeking lifestyle modification support

Abstract

BACKGROUND: Noncommunicable diseases are the leading cause of death worldwide. Cardiovascular and respiratory diseases, cancer, and type 2 diabetes share common risk factors that can be addressed: physical activity, a healthy diet, and avoiding smoking and alcohol. The Watching the Risk Factors (WARIFA) mobile health app was created for general health awareness and to support users in adopting healthier behaviors, as well as to support type 1 diabetes (T1D) self-management. OBJECTIVE: This study aims to evaluate the effectiveness of the WARIFA app with personalized artificial intelligence (AI)-driven messages, compared to a nonpersonalized version, in promoting health-related behavior change among the general population and individuals with T1D. METHODS: A total of 108 European participants, including individuals with T1D, were to be randomized (computer-generated sequence, double-blind, 1:1 ratio) to an intervention or control group. In the intervention group, participants used the WARIFA app with personalized messages and the use of AI. This applied to certain functionalities, such as providing recommendations on healthy dietary habits based on food logging and offering advice and encouragement through daily step tracking. It also provided risk predictions for cardiovascular and respiratory diseases, cancer, and type 2 diabetes. Participants with T1D were offered glucose predictions based on previous measurements. In the control group, participants used a WARIFA app without personalized messages or AI. Both WARIFA app versions offered access to air quality and UV index information for the geographical area, as well as displaying physical activity in the form of daily steps and sleep hours, as well as glucose results for participants with T1D. Both groups were provided with an activity monitor and used the WARIFA app for 8-12 weeks. The primary outcome is a self-defined goal, chosen from a set of proposed objectives at baseline and assessed at the end of the study using a Likert scale (1 to 10 points, 0 being no achievement at all and 10 being full achievement of the objective). Secondary outcomes include: engagement with the app, changes in lifestyle behavior, body composition, lipid profile, glycated hemoglobin (T1D only), hypoglycemic events (T1D only), and health-related quality of life, as well as acquired knowledge, self-efficacy, and usability. RESULTS: The clinical trial took place between January and June 2025. A total of 88 participants were finally recruited. The data are being analyzed, and the results are expected to be published in 2026. CONCLUSIONS: There is evidence that improving lifestyle behavior can prevent noncommunicable diseases. In this study, we aim to evaluate the effectiveness of the WARIFA app to improve lifestyle behaviors and T1D management. TRIAL REGISTRATION: ClinicalTrials.gov NCT06918444; https://clinicaltrials.gov/study/NCT06918444. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/84510.