Predicting stimulated C-peptide in type 1 diabetes using machine learning: a web-based tool from the T1D exchange registry

IF 7.4 3区医学 Q1 ENDOCRINOLOGY & METABOLISM

Diabetes research and clinical practice Pub Date : 2025-09-04 DOI:10.1016/j.diabres.2025.112453

Emre Sedar Saygili , Adnan Batman , Ersen Karakilic

{"title":"Predicting stimulated C-peptide in type 1 diabetes using machine learning: a web-based tool from the T1D exchange registry","authors":"Emre Sedar Saygili , Adnan Batman , Ersen Karakilic","doi":"10.1016/j.diabres.2025.112453","DOIUrl":null,"url":null,"abstract":"<div><h3>Aims</h3><div>The mixed-meal tolerance test (MMTT), though considered the gold standard for evaluating residual beta-cell function in type 1 diabetes mellitus (T1D), is impractical for routine use. We aimed to develop and validate a machine learning (ML) model to predict MMTT-stimulated C-peptide categories using routine clinical data.</div></div><div><h3>Methods</h3><div>Data from 319 individuals in the T1D Exchange Registry with complete MMTT and clinical information were analyzed. The cohort was randomly split into training (70%) and test (30%) sets. Five clinical variables—age at diagnosis, diabetes duration, HbA1c, non-fasting glucose, and non-fasting C-peptide—were selected via recursive feature elimination. Four ML algorithms (random forest [RF], XGBoost, LightGBM, and ordinal logistic regression) were trained with 10-fold cross-validation.</div></div><div><h3>Results</h3><div>The RF model showed the highest performance: AUC 0.94 (95% CI: 0.92–0.96), sensitivity 0.84 (95% CI: 0.80–0.89), and specificity 0.92 (95% CI: 0.90–0.94) in cross-validation. In the test set, AUC was 0.97, sensitivity 88%, and specificity 94%. Notably, 17.7% of individuals with undetectable non-fasting C-peptide had measurable levels after MMTT.</div></div><div><h3>Conclusions</h3><div>This ML model provides a practical, non-invasive tool for estimating beta-cell function in T1D and is available online at <span><span>https://cpeptide.streamlit.app</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":11249,"journal":{"name":"Diabetes research and clinical practice","volume":"229 ","pages":"Article 112453"},"PeriodicalIF":7.4000,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diabetes research and clinical practice","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S016882272500467X","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}

引用次数: 0

Abstract

Aims

The mixed-meal tolerance test (MMTT), though considered the gold standard for evaluating residual beta-cell function in type 1 diabetes mellitus (T1D), is impractical for routine use. We aimed to develop and validate a machine learning (ML) model to predict MMTT-stimulated C-peptide categories using routine clinical data.

Methods

Data from 319 individuals in the T1D Exchange Registry with complete MMTT and clinical information were analyzed. The cohort was randomly split into training (70%) and test (30%) sets. Five clinical variables—age at diagnosis, diabetes duration, HbA1c, non-fasting glucose, and non-fasting C-peptide—were selected via recursive feature elimination. Four ML algorithms (random forest [RF], XGBoost, LightGBM, and ordinal logistic regression) were trained with 10-fold cross-validation.

Results

The RF model showed the highest performance: AUC 0.94 (95% CI: 0.92–0.96), sensitivity 0.84 (95% CI: 0.80–0.89), and specificity 0.92 (95% CI: 0.90–0.94) in cross-validation. In the test set, AUC was 0.97, sensitivity 88%, and specificity 94%. Notably, 17.7% of individuals with undetectable non-fasting C-peptide had measurable levels after MMTT.

Conclusions

This ML model provides a practical, non-invasive tool for estimating beta-cell function in T1D and is available online at https://cpeptide.streamlit.app.

查看原文本刊更多论文

使用机器学习预测1型糖尿病的刺激c肽：来自T1D交换注册的基于网络的工具。

目的：混合膳食耐受试验（MMTT）虽然被认为是评估1型糖尿病（T1D）残余β细胞功能的金标准，但不适合常规使用。我们旨在开发和验证机器学习（ML）模型，以使用常规临床数据预测mmtt刺激的c肽类别。方法：分析来自319例T1D交换注册中心的数据，这些数据具有完整的MMTT和临床信息。队列随机分为训练组（70%）和测试组（30%）。5个临床变量：诊断年龄、糖尿病病程、糖化血红蛋白（HbA1c）、非空腹血糖、非空腹c肽。四种机器学习算法（随机森林[RF]、XGBoost、LightGBM和有序逻辑回归）进行了10倍交叉验证的训练。结果：交叉验证中，RF模型的AUC为0.94 (95% CI: 0.92 ~ 0.96)，灵敏度为0.84 (95% CI: 0.80 ~ 0.89)，特异性为0.92 （95% CI: 0.90 ~ 0.94）。在测试集中，AUC为0.97，灵敏度为88%，特异性为94%。值得注意的是，17.7%的非空腹c肽检测不到的个体在MMTT后有可测量的水平。结论：该ML模型为估计T1D中β细胞功能提供了一种实用、无创的工具，可在https://cpeptide.streamlit.app上在线获取。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Diabetes research and clinical practice 医学-内分泌学与代谢

CiteScore

10.30

自引率

3.90%

发文量

862

审稿时长

32 days

期刊介绍： Diabetes Research and Clinical Practice is an international journal for health-care providers and clinically oriented researchers that publishes high-quality original research articles and expert reviews in diabetes and related areas. The role of the journal is to provide a venue for dissemination of knowledge and discussion of topics related to diabetes clinical research and patient care. Topics of focus include translational science, genetics, immunology, nutrition, psychosocial research, epidemiology, prevention, socio-economic research, complications, new treatments, technologies and therapy.