A review on type 1 diabetes prediction methods

View at publisher Summarise with VIRAT
Authors: Rahul Ranjan, Mohd Haroon
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Type 1 diabetes (T1D) is a chronic condition impacting globally, with increasing prevalence due to environmental, genetic, and lifestyle factors. Traditional methods for predicting T1D progression and tailoring treatments are subjective and imprecise, and lead towards delay in treatment. Prediction models based on AI are offering accurate, data-driven approach to manage T1D by identification of high-risk patients and prediction of treatment responses effectively. This paper reviews research work on AI techniques for T1D progression, categorizing methods into mathematical, machine learning (ML), and deep learning (DL) approaches. Findings reveal that machine learning, shows strong performance. Challenges in current models include the need for feature selection tools, interpretable models for clinicians, and validation on large data. Future directions are emphasizing for model interpretability, expert-informed validation as well as feature importance analysis.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Diabetes and associated disorders Diabetes Management and Research

Publication details

Journal / source
CRC Press eBooks
Pages
64–67
Publication date
27 March 2026
Language
EN
Document type
Book chapter