Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines
JMIR Formative Research · 2026-05-15 · 10 · e81039-e81039
DOI: 10.2196/81039 ↗At a glance
Leitlinie in JMIR Formative Research, published online on 2026-05-15. Written by Jalilah Fllatah and 1 co-authors. Institution: Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, P.O. Box 80200, Jeddah, 21589, Saudi Arab…. Major MEDLINE topics: Diabetes Mellitus, Type 1, Risk Assessment, Decision Support Systems, Clinical, Diabetes Complications. Cited 1 times so far (Crossref); 37 references. The full text is freely available in PubMed Central.
Topics: Künstliche Intelligenz in der Pflege, Diabetes mellitus, Kinderkrankenpflege
Abstract (original language)
Background
Complication risks in children and adolescents with type 1 diabetes (T1D) can lead to serious health outcomes if not detected early. Despite the availability of clinical data, there remains a gap in interpretable tools that support risk stratification in this age group, particularly in alignment with local clinical guidelines.
Objective
The purpose of this study is to develop a clinically interpretable model that classifies the risk levels of T1D complications—acute, chronic, and low—using real-world data and expert clinical rules derived from the Saudi Diabetes Clinical Practice Guidelines.
Methods
A pediatric T1D dataset comprising of 306 patients was preprocessed through structured cleaning and feature engineering. Risk labels were constructed using Saudi Diabetes Clinical Practice Guidelines–derived rules. Feature selection was performed using a hybrid approach that combined the SHAP (Shapley Additive Explanations) analysis with exhaustive feature selection. A decision tree model was trained and optimized via cross-validation, using the F 1 -score as the primary performance metric.
Results
The final model achieved a high mean F 1 -score of 0.9876 with a low variance of 0.0189, using only 5 clinical features: BMI, hypoglycemia, disease duration, hemoglobin A 1c , and impaired glucose metabolism. These features were consistently ranked as the most influential. The resulting decision tree offered a transparent logic path, enhancing its clinical interpretability and usability.
Conclusions
This study demonstrates that a simple and interpretable model, guided by national clinical guidelines, can effectively predict the risk levels of T1D complications in children and adolescents. Its strong performance, clarity, and reliance on a small number of clinically meaningful features make it a promising candidate for integration into clinical decision support systems. This supports a shift toward predictive and personalized diabetes care.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, P.O. Box 80200, Jeddah, 21589, Saudi Arabia, 966 544027109.
- Center of Research Excellence in Artificial Intelligence and Data Science, King Abdulaziz University, Jeddah, Saudi Arabia.
- Institute of Genomic Medicine Sciences, King Abdulaziz University, Jeddah, Saudi Arabia.
- Centre of Artificial Intelligence in Precision Medicines, King Abdulaziz University, Jeddah, Saudi Arabia.
ORCID profiles: Jalilah Fllatah, Haneen Banjar
Cite
APA
Fllatah, J., & Banjar, H. (2026). Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines. JMIR Formative Research, 10, e81039-e81039. https://doi.org/10.2196/81039
Vancouver
Fllatah J, Banjar H. Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines. JMIR Formative Research. 2026;10:e81039-e81039. doi:10.2196/81039
BibTeX
@article{Fllatah2026,
author = {Fllatah, Jalilah and Banjar, Haneen},
title = {Complication Risk Classification in Children and Adolescents With Type 1 Diabetes: Interpretable Machine Learning Study Based on Saudi Clinical Guidelines},
journal = {JMIR Formative Research},
year = {2026},
volume = {10},
pages = {e81039--e81039},
doi = {10.2196/81039}
}
EUVIMED