Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity

AimWe aimed to develop and internally validate a machine learning (ML)-based model for the prediction of the risk of type 2 diabetes mellitus (T2DM) in children with obesity.MethodsIn total, 292 children with obesity and T2DM were enrolled between July 2023 and February 2024 and followed for at leas...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin-Xia Yang, Yue Liu, Rong Huang, Hai-ying Wu, Ya-yun Wang, Su-ying Cao, Guo-ying Wang, Jian-Min Zhang, Zi-Sheng Ai, Hui-min Zhou
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1649988/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391199314509824
author Jin-Xia Yang
Jin-Xia Yang
Yue Liu
Yue Liu
Rong Huang
Hai-ying Wu
Ya-yun Wang
Su-ying Cao
Guo-ying Wang
Jian-Min Zhang
Zi-Sheng Ai
Hui-min Zhou
author_facet Jin-Xia Yang
Jin-Xia Yang
Yue Liu
Yue Liu
Rong Huang
Hai-ying Wu
Ya-yun Wang
Su-ying Cao
Guo-ying Wang
Jian-Min Zhang
Zi-Sheng Ai
Hui-min Zhou
author_sort Jin-Xia Yang
collection DOAJ
description AimWe aimed to develop and internally validate a machine learning (ML)-based model for the prediction of the risk of type 2 diabetes mellitus (T2DM) in children with obesity.MethodsIn total, 292 children with obesity and T2DM were enrolled between July 2023 and February 2024 and followed for at least 1 year. Eight ML algorithms (Decision Tree, Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron, Adaptive Boosting, Random Forest, Gradient Boosting Decision Tree, and Extreme Gradient Boosting) were compared for their capacity to identify key clinical and laboratory characteristics of T2DM in children and to create a risk prediction model.ResultsForty-nine children were diagnosed with T2DM during the follow-up period. The SVM algorithm was the best predictor of T2DM, with the largest area under the receiver operating characteristic curve (0.98) and accuracy (93.2%). The SVM algorithm identified eight predictors: BMI, creatinine, prealbumin, glucose (180 min), glycosylated hemoglobin A1c, thyrotropin, total thyroxine (T4), and free T4 concentrations. Thus, an ML-based prediction model accurately identifies children with obesity at high risk of T2DM. If externally validated, this tool could facilitate early, personalized interventions aimed at preventing T2DM.DiscussionThe rising prevalence of obesity in childhood is associated with an increase in the risk of early-onset T2DM. Therefore, the early identification of individuals at high risk is crucial to prevent the development of this disease. In a comparative analysis of the performance of multiple ML algorithms, we found that the SVM algorithm was the best predictor of the development of T2DM.
format Article
id doaj-art-7779208f01764ad8b4e802dc2c4195d0
institution Kabale University
issn 1664-2392
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-7779208f01764ad8b4e802dc2c4195d02025-08-20T03:41:08ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-08-011610.3389/fendo.2025.16499881649988Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesityJin-Xia Yang0Jin-Xia Yang1Yue Liu2Yue Liu3Rong Huang4Hai-ying Wu5Ya-yun Wang6Su-ying Cao7Guo-ying Wang8Jian-Min Zhang9Zi-Sheng Ai10Hui-min Zhou11School of Medicine, Tongji University, Basic Medical Science, Shanghai, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaSchool of Medicine, Tongji University, Basic Medical Science, Shanghai, ChinaGongli Hospital, Pudong New District, Department of Orthopedic Surgery, Shanghai, ChinaShanghai First Maternity and Infant Hospital, School of Medicine, Tongji University, Shanghai, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaChildren’s Hospital of Soochow University, Department of Traditional Chinese Medical, Suzhou, ChinaSchool of Medicine, Tongji University, Basic Medical Science, Shanghai, ChinaChildren’s Hospital of Soochow University, Endocrine Genetic Metabolism, Suzhou, ChinaAimWe aimed to develop and internally validate a machine learning (ML)-based model for the prediction of the risk of type 2 diabetes mellitus (T2DM) in children with obesity.MethodsIn total, 292 children with obesity and T2DM were enrolled between July 2023 and February 2024 and followed for at least 1 year. Eight ML algorithms (Decision Tree, Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron, Adaptive Boosting, Random Forest, Gradient Boosting Decision Tree, and Extreme Gradient Boosting) were compared for their capacity to identify key clinical and laboratory characteristics of T2DM in children and to create a risk prediction model.ResultsForty-nine children were diagnosed with T2DM during the follow-up period. The SVM algorithm was the best predictor of T2DM, with the largest area under the receiver operating characteristic curve (0.98) and accuracy (93.2%). The SVM algorithm identified eight predictors: BMI, creatinine, prealbumin, glucose (180 min), glycosylated hemoglobin A1c, thyrotropin, total thyroxine (T4), and free T4 concentrations. Thus, an ML-based prediction model accurately identifies children with obesity at high risk of T2DM. If externally validated, this tool could facilitate early, personalized interventions aimed at preventing T2DM.DiscussionThe rising prevalence of obesity in childhood is associated with an increase in the risk of early-onset T2DM. Therefore, the early identification of individuals at high risk is crucial to prevent the development of this disease. In a comparative analysis of the performance of multiple ML algorithms, we found that the SVM algorithm was the best predictor of the development of T2DM.https://www.frontiersin.org/articles/10.3389/fendo.2025.1649988/fullobesitychildrenrisk prediction modelmachine learningtype 2 diabetes mellitus
spellingShingle Jin-Xia Yang
Jin-Xia Yang
Yue Liu
Yue Liu
Rong Huang
Hai-ying Wu
Ya-yun Wang
Su-ying Cao
Guo-ying Wang
Jian-Min Zhang
Zi-Sheng Ai
Hui-min Zhou
Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
Frontiers in Endocrinology
obesity
children
risk prediction model
machine learning
type 2 diabetes mellitus
title Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
title_full Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
title_fullStr Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
title_full_unstemmed Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
title_short Development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
title_sort development and internal validation of a machine learning algorithm for the risk of type 2 diabetes mellitus in children with obesity
topic obesity
children
risk prediction model
machine learning
type 2 diabetes mellitus
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1649988/full
work_keys_str_mv AT jinxiayang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT jinxiayang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT yueliu developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT yueliu developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT ronghuang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT haiyingwu developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT yayunwang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT suyingcao developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT guoyingwang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT jianminzhang developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT zishengai developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity
AT huiminzhou developmentandinternalvalidationofamachinelearningalgorithmfortheriskoftype2diabetesmellitusinchildrenwithobesity