Related Experiment Video
Updated: Jun 27, 2026
12:08
Improving IV Insulin Administration in a Community Hospital
Published on: June 11, 2012
An AI-Assisted Tool to Predict Continuous Glucose Monitor Adherence in Children With Type 1 Diabetes in Oman:
Thamra Al Ghafri1,2, Saud Al Harthi3, Asma Bait Ishaq1
1Directorate General of Health Services, Muscat, Oman.
JMIR Research Protocols
|June 25, 2026
Summary
This study developed OMNIdiasense, an AI tool to predict continuous glucose monitor (CGM) adherence in children with type 1 diabetes mellitus (T1DM). The tool aims to improve clinical outcomes and reduce waste by identifying at-risk patients before device dispensing.
Area of Science:
- Translational research in pediatric endocrinology and digital health.
- Application of artificial intelligence (AI) in diabetes management.
- Behavioral science and adherence research in chronic disease.
Background:
- Type 1 diabetes mellitus (T1DM) in children necessitates consistent self-management for optimal glycemic control and complication prevention.
- Continuous glucose monitoring (CGM) significantly aids pediatric diabetes care, but consistent device wear remains a challenge.
- Oman's national CGM initiative provides a unique opportunity to study adherence factors and develop predictive tools.
Purpose of the Study:
- To characterize Omani children with T1DM receiving CGM.
- To identify factors influencing optimal CGM use (demographic, psychosocial, lifestyle).
- To develop and validate OMNIdiasense, an AI tool predicting CGM adherence, and pilot its implementation.
Main Methods:
- Retrospective cohort analysis of CGM data and clinical outcomes (Sub-study 1).
- Cross-sectional, mixed-methods interviews with children (Optimizers vs. Sub-users) to identify psychosocial and behavioral correlates (Sub-study 2).
- Development and pilot testing of the AI tool (OMNIdiasense) through quasi-experimental and randomized controlled trials (Sub-study 3).
Main Results:
- The OMNIdiasense AI tool is designed as a decision-support adjunct, not a barrier to CGM access.
- Analysis of adherence prevalence and clinical predictors will inform AI model development.
- Psychosocial and behavioral factors will be integrated into the AI model for adherence prediction.
Conclusions:
- This program is the first in the GCC to integrate real-world CGM data, psychosocial measures, and local AI for predicting pediatric CGM adherence.
- OMNIdiasense aims to proactively support vulnerable patients, enhancing clinical benefits.
- The tool is expected to improve CGM adherence, leading to better glycemic control and reduced healthcare costs.