开发并验证基于机器学习的模型,以预测中老年人挑战后孤立性高血糖:一项多中心研究的分析

IF 4.6 2区 医学 Q1 ENDOCRINOLOGY & METABOLISM
Rui Hou, Jingtao Dou, Lijuan Wu, Xiaoyu Zhang, Changwei Li, Weiqing Wang, Zhengnan Gao, Xulei Tang, Li Yan, Qin Wan, Zuojie Luo, Guijun Qin, Lulu Chen, Jianguang Ji, Yan He, Wei Wang, Yiming Mu, Deqiang Zheng
{"title":"开发并验证基于机器学习的模型,以预测中老年人挑战后孤立性高血糖:一项多中心研究的分析","authors":"Rui Hou,&nbsp;Jingtao Dou,&nbsp;Lijuan Wu,&nbsp;Xiaoyu Zhang,&nbsp;Changwei Li,&nbsp;Weiqing Wang,&nbsp;Zhengnan Gao,&nbsp;Xulei Tang,&nbsp;Li Yan,&nbsp;Qin Wan,&nbsp;Zuojie Luo,&nbsp;Guijun Qin,&nbsp;Lulu Chen,&nbsp;Jianguang Ji,&nbsp;Yan He,&nbsp;Wei Wang,&nbsp;Yiming Mu,&nbsp;Deqiang Zheng","doi":"10.1002/dmrr.3832","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Introduction</h3>\n \n <p>Due to the high cost and complexity, the oral glucose tolerance test is not adopted as the screening method for identifying diabetes patients, which leads to the misdiagnosis of patients with isolated post-challenge hyperglycemia (IPH), that is., patients with normal fasting plasma glucose (&lt;7.0 mmoL/L) and abnormal 2-h postprandial blood glucose (≥11.1 mmoL/L). We aimed to develop a model to differentiate individuals with IPH from the normal population.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Data from 54301 eligible participants were obtained from the Risk Evaluation of Cancers in Chinese Diabetic Individuals: a longitudinal (REACTION) study in China. Data from 37740 participants were used to develop the diagnostic system. External validation was performed among 16561 participants. Three machine learning algorithms were used to create the predictive models, which were further evaluated by various classification algorithms to establish the best predictive model.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Ten features were selected to develop an IPH diagnosis system (IPHDS) based on an artificial neural network. In external validation, the AUC of the IPHDS was 0.823 (95% CI 0.811–0.836), which was significantly higher than the AUC of the Taiwan model [0.799 (0.786–0.813)] and that of the Chinese Diabetes Risk Score model [0.648 (0.635–0.662)]. The IPHDS model had a sensitivity of 75.6% and a specificity of 74.6%. This model outperformed the Taiwan and CDRS models in subgroup analyses. An online site with instant predictions was deployed at https://app-iphds-e1fc405c8a69.herokuapp.com/.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The proposed IPHDS could be a convenient and user-friendly screening tool for diabetes during health examinations in a large general population.</p>\n </section>\n </div>","PeriodicalId":11335,"journal":{"name":"Diabetes/Metabolism Research and Reviews","volume":"40 5","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/dmrr.3832","citationCount":"0","resultStr":"{\"title\":\"Development and validation of a machine learning-based model to predict isolated post-challenge hyperglycemia in middle-aged and elder adults: Analysis from a multicentric study\",\"authors\":\"Rui Hou,&nbsp;Jingtao Dou,&nbsp;Lijuan Wu,&nbsp;Xiaoyu Zhang,&nbsp;Changwei Li,&nbsp;Weiqing Wang,&nbsp;Zhengnan Gao,&nbsp;Xulei Tang,&nbsp;Li Yan,&nbsp;Qin Wan,&nbsp;Zuojie Luo,&nbsp;Guijun Qin,&nbsp;Lulu Chen,&nbsp;Jianguang Ji,&nbsp;Yan He,&nbsp;Wei Wang,&nbsp;Yiming Mu,&nbsp;Deqiang Zheng\",\"doi\":\"10.1002/dmrr.3832\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Introduction</h3>\\n \\n <p>Due to the high cost and complexity, the oral glucose tolerance test is not adopted as the screening method for identifying diabetes patients, which leads to the misdiagnosis of patients with isolated post-challenge hyperglycemia (IPH), that is., patients with normal fasting plasma glucose (&lt;7.0 mmoL/L) and abnormal 2-h postprandial blood glucose (≥11.1 mmoL/L). We aimed to develop a model to differentiate individuals with IPH from the normal population.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>Data from 54301 eligible participants were obtained from the Risk Evaluation of Cancers in Chinese Diabetic Individuals: a longitudinal (REACTION) study in China. Data from 37740 participants were used to develop the diagnostic system. External validation was performed among 16561 participants. Three machine learning algorithms were used to create the predictive models, which were further evaluated by various classification algorithms to establish the best predictive model.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>Ten features were selected to develop an IPH diagnosis system (IPHDS) based on an artificial neural network. In external validation, the AUC of the IPHDS was 0.823 (95% CI 0.811–0.836), which was significantly higher than the AUC of the Taiwan model [0.799 (0.786–0.813)] and that of the Chinese Diabetes Risk Score model [0.648 (0.635–0.662)]. The IPHDS model had a sensitivity of 75.6% and a specificity of 74.6%. This model outperformed the Taiwan and CDRS models in subgroup analyses. An online site with instant predictions was deployed at https://app-iphds-e1fc405c8a69.herokuapp.com/.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>The proposed IPHDS could be a convenient and user-friendly screening tool for diabetes during health examinations in a large general population.</p>\\n </section>\\n </div>\",\"PeriodicalId\":11335,\"journal\":{\"name\":\"Diabetes/Metabolism Research and Reviews\",\"volume\":\"40 5\",\"pages\":\"\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-06-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/dmrr.3832\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Diabetes/Metabolism Research and Reviews\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/dmrr.3832\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diabetes/Metabolism Research and Reviews","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/dmrr.3832","RegionNum":2,"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

摘要

引言 由于口服葡萄糖耐量试验成本高、操作复杂,没有被作为糖尿病患者的筛查方法,导致孤立性挑战后高血糖(IPH)患者被误诊,即空腹血浆葡萄糖正常(<7.0 mmoL/L)而餐后 2 小时血糖异常(≥11.1 mmoL/L)的患者。我们的目的是建立一个模型,将 IPH 患者与正常人群区分开来。 方法 我们从中国糖尿病患者癌症风险评估纵向研究(REACTION)中获得了 54301 名合格参与者的数据。来自 37740 名参与者的数据被用于开发诊断系统。在 16561 名参与者中进行了外部验证。使用三种机器学习算法创建预测模型,并通过各种分类算法对其进行进一步评估,以建立最佳预测模型。 结果 选定了十个特征,开发出基于人工神经网络的 IPH 诊断系统(IPHDS)。在外部验证中,IPHDS的AUC为0.823(95% CI 0.811-0.836),明显高于台湾模型的AUC[0.799(0.786-0.813)]和中国糖尿病风险评分模型的AUC[0.648(0.635-0.662)]。IPHDS 模型的灵敏度为 75.6%,特异度为 74.6%。在亚组分析中,该模型优于台湾模型和 CDRS 模型。可即时预测的在线网站已部署在 https://app-iphds-e1fc405c8a69.herokuapp.com/ 上。 结论 建议的 IPHDS 可作为一种方便易用的糖尿病筛查工具,适用于大量普通人群的健康检查。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Development and validation of a machine learning-based model to predict isolated post-challenge hyperglycemia in middle-aged and elder adults: Analysis from a multicentric study

Development and validation of a machine learning-based model to predict isolated post-challenge hyperglycemia in middle-aged and elder adults: Analysis from a multicentric study

Introduction

Due to the high cost and complexity, the oral glucose tolerance test is not adopted as the screening method for identifying diabetes patients, which leads to the misdiagnosis of patients with isolated post-challenge hyperglycemia (IPH), that is., patients with normal fasting plasma glucose (<7.0 mmoL/L) and abnormal 2-h postprandial blood glucose (≥11.1 mmoL/L). We aimed to develop a model to differentiate individuals with IPH from the normal population.

Methods

Data from 54301 eligible participants were obtained from the Risk Evaluation of Cancers in Chinese Diabetic Individuals: a longitudinal (REACTION) study in China. Data from 37740 participants were used to develop the diagnostic system. External validation was performed among 16561 participants. Three machine learning algorithms were used to create the predictive models, which were further evaluated by various classification algorithms to establish the best predictive model.

Results

Ten features were selected to develop an IPH diagnosis system (IPHDS) based on an artificial neural network. In external validation, the AUC of the IPHDS was 0.823 (95% CI 0.811–0.836), which was significantly higher than the AUC of the Taiwan model [0.799 (0.786–0.813)] and that of the Chinese Diabetes Risk Score model [0.648 (0.635–0.662)]. The IPHDS model had a sensitivity of 75.6% and a specificity of 74.6%. This model outperformed the Taiwan and CDRS models in subgroup analyses. An online site with instant predictions was deployed at https://app-iphds-e1fc405c8a69.herokuapp.com/.

Conclusions

The proposed IPHDS could be a convenient and user-friendly screening tool for diabetes during health examinations in a large general population.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Diabetes/Metabolism Research and Reviews
Diabetes/Metabolism Research and Reviews 医学-内分泌学与代谢
CiteScore
17.20
自引率
2.50%
发文量
84
审稿时长
4-8 weeks
期刊介绍: Diabetes/Metabolism Research and Reviews is a premier endocrinology and metabolism journal esteemed by clinicians and researchers alike. Encompassing a wide spectrum of topics including diabetes, endocrinology, metabolism, and obesity, the journal eagerly accepts submissions ranging from clinical studies to basic and translational research, as well as reviews exploring historical progress, controversial issues, and prominent opinions in the field. Join us in advancing knowledge and understanding in the realm of diabetes and metabolism.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信