Related Experiment Video
Updated: Jun 27, 2026
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.
Insights
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.
Background:
Type 1 diabetes mellitus (T1DM) in children requires sustained self-management to achieve glycemic targets. Continuous glucose monitoring (CGM) has transformed pediatric diabetes care; yet, adherence to device wear remains inconsistent. In May 2024, Oman launched a national initiative distributing CGMs to children with T1DM across all governorates, creating a real-world opportunity to study adherence determinants and to develop a locally validated AI-assisted predictive tool.
Objective:
This multiphase translational research project aims to (1) characterize the population of Omani children with T1DM; (2) identify demographic, psychosocial, dietary, and physical activity correlates of optimal CGM use; (3) develop, train, and validate an AI-assisted behavioral predictive tool "OMNIdiasense" to forecast CGM adherence prior to device dispensing; and (4) pilot test the OMNIdiasense tool.
Methods:
Three sequential, interlinked substudies will be conducted. Substudy 1 is a retrospective cohort analysis of routinely collected Al Shifa data for all children who received CGMs between July 2024 and February 2025, with glycemic, anthropometric, and laboratory outcomes compared at baseline and at ≥3 months. Outputs on adherence prevalence, and clinical predictors become the structured input layer for the proposed AI model. Substudy 2 is a cross-sectional, mixed methods study using face-to-face structured interviews with a randomly selected sample of children aged 10-18 years, classified as "CGM optimizers" (≥6 days/week) or "CGM subusers" (<6 days/week or discontinued); responses across validated behavioral, stress, and dietary instruments are compared. Outputs are the psychosocial and behavioral feature set, qualitative themes, and effect sizes that drive feature selection for the AI model. Substudy 3 develops the AI tool (OMNIdiasense), comprising (1) a quasi-experimental single-arm pilot among 100 existing CGM subusers and (2) a parallel pilot randomized controlled trial (n=50; 25 intervention, 25 control) among newly diagnosed children, with assessments at baseline, 3, 6, and 12 months. The primary outcome is between-group difference in CGM adherence; secondary outcomes include hemoglobin A1c, anthropometric, cardiovascular, and laboratory measures, and barriers to use. Reporting will follow SPIRIT (Standard Protocol Items: Recommendations for Interventional Trials) 2025 (interventional component), STROBE (Strengthening the Reporting of Observational Studies in Epidemiology; observational component), the CONSORT (Consolidated Standards of Reporting Trials) 2025 extension for pilot and feasibility trials, COREQ (Consolidated Criteria for Reporting Qualitative Research; qualitative component), and TRIPOD+AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis + Artificial Intelligence; predictive model).
Results:
The proposed AI tool is intended as a decision-support adjunct and not a gatekeeping mechanism for CGM access.
Conclusions:
To our knowledge, OMNIdiasense is the first AI tool in the Gulf Cooperation Council region to predict pediatric CGM adherence. By targeting behaviorally vulnerable patients before sensor distribution, OMNIdiasense is expected to support clinical benefit and reduce financial waste.
Trial Registration:
ISRCTN Registry ISRCTN15827616; https://doi.org/10.1186/ISRCTN15827616.
International Registered Report Identifier (Irrid):
DERR1-10.2196/99626.