Article(id=1241036244667396393, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241036242561855785, articleNumber=null, orderNo=null, doi=10.20043/j.cnki.MPM.202503082, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1741104000000, receivedDateStr=2025-03-05, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773815698067, onlineDateStr=2026-03-18, pubDate=1756051200000, pubDateStr=2025-08-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773815698067, onlineIssueDateStr=2026-03-18, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773815698067, creator=13701087609, updateTime=1773815698067, updator=13701087609, issue=Issue{id=1241036242561855785, tenantId=1146029695717560320, journalId=1227665162245664772, year='2025', volume='52', issue='16', pageStart='2881', pageEnd='3072', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773815697565, creator=13701087609, updateTime=1773840190562, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241138973712634304, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241036242561855785, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241138973712634305, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241036242561855785, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=2894, endPage=2899, ext={EN=ArticleExt(id=1241036245393010989, articleId=1241036244667396393, tenantId=1146029695717560320, journalId=1227665162245664772, language=EN, title=Prediction model of metabolic syndrome for railway workers based on machine learning algorithm, columnId=1228016567443718970, journalTitle=Modern Preventive Medicine, columnName=Epidemiology and Statistical Methods Advances, runingTitle=null, highlight=null, articleAbstract=
Objective

To construct a prediction model for metabolic syndrome (Metabolic Syndrome, MetS) in railway employees based on machine learning algorithms (Machine Learning, ML) and evaluate the prediction performance.

Methods

The time to the onset of metabolic syndrome was used as the outcome variable, with demographic characteristics and biochemical indicators as predictive variables. Univariate analysis was conducted to select predictive indicators. The study subjects were randomly divided into a training set and a test set in a 7:3 ratio. Cox proportional hazards regression, Random Forest (Random Survival Forest, RSF), and Gradient Boosting Machine (Gradient Boosting Machine, GBM) were used to build metabolic syndrome prediction models. Model performance was assessed using the area under the receiver operating characteristic curve (Area under curve, AUC), concordance index (C-index), sensitivity, specificity, accuracy, and F1 score. A risk calculator was created using the shiny package.

Results

This study included 17 087 subjects and collected 28 indicators. Univariate analysis identified 22 statistically significant indicators. In the training set, the areas under the curve (area under the curve, AUC) of the prediction models constructed by Cox, RSF, and GBM were 0.870,0.938, and 0.891, respectively; C-index values were 0.853,0.935, and 0.843; sensitivity was 0.612,0.968, and 0.628; specificity was 0.933,0.742, and 0.994; accuracy was 0.678,0.788, and 0.703; F1 scores were 0.751,0.839, and 0.749.

Conclusion

The RSF model outperformed the Cox model and the GBM model in predicting metabolic syndrome among railway employees, providing a scientific basis for early identification of metabolic syndrome and aiding in the implementation of primary prevention measures.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Qiong WU, Yu-tian WEI, Wei-heng SUN, Li-shun XIAO, Xiao-na CONG, Bin HU), CN=ArticleExt(id=1241036247116869964, articleId=1241036244667396393, tenantId=1146029695717560320, journalId=1227665162245664772, language=CN, title=基于机器学习算法构建铁路职工代谢综合征预测模型, columnId=1228016567632462653, journalTitle=现代预防医学, columnName=流行病与统计方法, runingTitle=null, highlight=null, articleAbstract=
目的

基于机器学习算法(Machine Learning,ML)构建铁路职工代谢综合征(Metabolic Syndrome,MetS)预测模型并对预测效果进行评价。

方法

以是否出现代谢综合征为结局变量,以人口学特征和生化指标为预测变量,采用单因素分析筛选出预测指标。将研究对象按7:3的比例随机划分成训练集和测试集,分别采用Cox比例风险回归、随机生存森林(Random Survival Forest,RSF)和梯度提升机(Gradient Boosting Machine,GBM)建立代谢综合征预测模型,采用受试者工作特征曲线下面积(Area under curve,AUC)、一致性指标(C-index)、灵敏度、特异度、准确度、F1分数评估模型性能。借助shiny程序包绘制风险计算器。

结果

本研究共纳入17 087名研究对象,共采集28项指标,单因素分析筛选出22个有统计学意义的指标。在训练集中,Cox、RSF和GBM模型构建的预测模型AUC分别为0.870、0.938和0.891;C-index分别为0.853、0.935和0.843;灵敏度分别为0.612、0.968和0.628;特异度分别为0.933、0.742和0.994;准确度分别为0.678、0.788和0.703;F1分数分别为0.751、0.839和0.749。

结论

RSF模型在预测铁路员工代谢综合征方面表现优于Cox模型和GBM模型,为早期识别代谢综合征提供了科学依据,并有助于推动一级预防措施的实施。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
胡斌,E-mail:
, copyrightStatement=本刊刊出的所有文章不代表中华预防医学会和本刊编委会的观点,除非特别声明。, copyrightOwner=中华预防医学会和四川大学华西公共卫生学院, extLink=null, articleAbsUrl=null, sourceXml=yURQet3HLnSua0ahzGYLEg==, magXml=YBc7Oj+BVkJpW2NDeztAHA==, pdfUrl=null, pdf=P+foC6JyEfJWxQ2tXvmUQA==, pdfFileSize=811283, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uiuTHZ1QjXPWErS1CDG9Lg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VlX/ljv0pM0P8+ARtJOuVg==, mapNumber=null, authorCompany=null, fund=null, authors=

吴琼(2001—),女,硕士在读,研究方向:公共卫生

, authorsList=吴琼, 卫雨甜, 孙伟恒, 肖立顺, 丛晓娜, 胡斌)}, authors=[Author(id=1241057504822620673, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057504910701062, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057504822620673, language=EN, stringName=Qiong WU, firstName=Qiong, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057504986198537, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057504822620673, language=CN, stringName=吴琼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.徐州医科大学公共卫生学院,江苏 徐州 221004, bio={"content":"

吴琼(2001—),女,硕士在读,研究方向:公共卫生

"}, bioImg=null, bioContent=

吴琼(2001—),女,硕士在读,研究方向:公共卫生

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)])]), Author(id=1241057505086861840, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057505204302360, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505086861840, language=EN, stringName=Yu-tian WEI, firstName=Yu-tian, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057505304965665, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505086861840, language=CN, stringName=卫雨甜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.徐州医科大学公共卫生学院,江苏 徐州 221004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)])]), Author(id=1241057505384657451, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057505472737843, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505384657451, language=EN, stringName=Wei-heng SUN, firstName=Wei-heng, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057505569206842, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505384657451, language=CN, stringName=孙伟恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.徐州医科大学公共卫生学院,江苏 徐州 221004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)])]), Author(id=1241057505665675840, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057505791504970, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505665675840, language=EN, stringName=Li-shun XIAO, firstName=Li-shun, middleName=null, lastName=XIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057505892168273, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057505665675840, language=CN, stringName=肖立顺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.徐州医科大学公共卫生学院,江苏 徐州 221004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)])]), Author(id=1241057506005414491, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057506093494887, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057506005414491, language=EN, stringName=Xiao-na CONG, firstName=Xiao-na, middleName=null, lastName=CONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057506202546805, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057506005414491, language=CN, stringName=丛晓娜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.中国铁路上海局集团有限公司上海铁路疾病预防控制所, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504713568762, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=2., ext=[AuthorCompanyExt(id=1241057504721957370, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504713568762, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国铁路上海局集团有限公司上海铁路疾病预防控制所)])]), Author(id=1241057506319987325, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hubin@xzhmu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241057506462593673, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057506319987325, language=EN, stringName=Bin HU, firstName=Bin, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241057506601005717, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, authorId=1241057506319987325, language=CN, stringName=胡斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.徐州医科大学公共卫生学院,江苏 徐州 221004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)])])], keywords=[Keyword(id=1241057506814915243, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, orderNo=1, keyword=Random survival forest), Keyword(id=1241057506982687420, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, orderNo=2, keyword=Cox regression model), Keyword(id=1241057507100127943, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, orderNo=3, keyword=Gradient Boosting Machine), Keyword(id=1241057507192402636, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, orderNo=4, keyword=Metabolic syndrome), Keyword(id=1241057507347591895, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, orderNo=5, keyword=Machine learning), Keyword(id=1241057507481809638, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, orderNo=1, keyword=随机生存森林), Keyword(id=1241057507603444463, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, orderNo=2, keyword=Cox回归模型), Keyword(id=1241057507737662203, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, orderNo=3, keyword=梯度提升机), Keyword(id=1241057507880268551, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, orderNo=4, keyword=代谢综合征), Keyword(id=1241057507976737551, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, orderNo=5, keyword=机器学习)], refs=[Reference(id=1241057509889340337, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=5, pageStart=811, pageEnd=816, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=杜懿涵, 陆崇, 冯小燕, journalName=现代预防医学, refType=null, unstructuredReference=杜懿涵,陆崇,冯小燕,等.铁路职工夜班工作与代谢综合征的关联性分析[J].现代预防医学2024,51(5):811-816., articleTitle=铁路职工夜班工作与代谢综合征的关联性分析, refAbstract=null), Reference(id=1241057510048723900, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=5, pageStart=811, pageEnd=816, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Du YH, Lu C, Feng XY, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Du YH, Lu C, Feng XY, et al. Analysis of the relationship between night shift work and metabolic syndrome in railway workers[J]. Modern Preventive Medicine, 2024, 51(5): 811-816. (In Chinese), articleTitle=Analysis of the relationship between night shift work and metabolic syndrome in railway workers, refAbstract=null), Reference(id=1241057510178747335, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=2, pageStart=239, pageEnd=244, 262, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=杨波, 冯传腾, 于文倩, journalName=现代预防医学, refType=null, unstructuredReference=杨波,冯传腾,于文倩,等.铁路职业人群夜班轮班工作与代谢综合征的关联及中介效应分析[J].现代预防医学2023,50(2):239-244, 262., articleTitle=铁路职业人群夜班轮班工作与代谢综合征的关联及中介效应分析, refAbstract=null), Reference(id=1241057510413628369, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=2, pageStart=239, pageEnd=244, 262, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Yang B, Feng CT, Yu WQ, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Yang B, Feng CT, Yu WQ, et al. Association and mediating effects of night shift work on metabolic syndrome in railway professional workers[J]. Modern Preventive Medicine, 2023, 50(2): 239-244, 262. (In Chinese), articleTitle=Association and mediating effects of night shift work on metabolic syndrome in railway professional workers, refAbstract=null), Reference(id=1241057510526874589, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=52, issue=2, pageStart=376, pageEnd=380, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=于跃, 白国霞, 扎西宗吉, journalName=现代预防医学, refType=null, unstructuredReference=于跃,白国霞,扎西宗吉,等.西藏中老年人代谢综合征患病现状及危险因素分析[J].现代预防医学2025,52(2):376-380., articleTitle=西藏中老年人代谢综合征患病现状及危险因素分析, refAbstract=null), Reference(id=1241057510673675237, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=52, issue=2, pageStart=376, pageEnd=380, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Yu Y, Bai GX, Za XZJ, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Yu Y, Bai GX, Za XZJ, et al. Prevalence and risk factors of metabolic syndrome among middle-aged and elderly People in Tibet[J]. Modern Preventive Medicine, 2025, 52(2): 376-380. (In Chinese), articleTitle=Prevalence and risk factors of metabolic syndrome among middle-aged and elderly People in Tibet, refAbstract=null), Reference(id=1241057510828864496, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2022, volume=18, issue=4, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Gharipour M, Nezafati PY, Sadeghian L, journalName=ARYA Atherosclerosis, refType=null, unstructuredReference=Gharipour M, Nezafati PY, Sadeghian L, et al. Precision medicine and metabolic syndrome[J]. ARYA Atherosclerosis, 2022, 18(4): 1-10., articleTitle=Precision medicine and metabolic syndrome, refAbstract=null), Reference(id=1241057510992442363, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2022, volume=23, issue=2, pageStart=786, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Fahed G, Aoun L, Bou zerdan M, journalName=International Journal of Molecular Sciences, refType=null, unstructuredReference=Fahed G, Aoun L, Bou zerdan M, et al. Metabolic syndrome: updates on pathophysiology and management in 2021[J]. International Journal of Molecular Sciences, 2022, 23(2): 786., articleTitle=Metabolic syndrome: updates on pathophysiology and management in 2021, refAbstract=null), Reference(id=1241057511126660098, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=22, pageStart=3157, pageEnd=3166, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=中国医师协会中西医结合医师分会内分泌与代谢病学专业委员会, journalName=世界中医药, refType=null, unstructuredReference=中国医师协会中西医结合医师分会内分泌与代谢病学专业委员会.代谢综合征病证结合诊疗指南[J].世界中医药2023,18(22):3157-3166., articleTitle=代谢综合征病证结合诊疗指南, refAbstract=null), Reference(id=1241057511248293895, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=22, pageStart=3157, pageEnd=3166, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Endocrinology and Metabolic Diseases Committee of Integrated Traditional Chinese and Western Medicine Branch of Chinese Medical Doctor Association, journalName=World Traditional Chinese Medicine, refType=null, unstructuredReference=Endocrinology and Metabolic Diseases Committee of Integrated Traditional Chinese and Western Medicine Branch of Chinese Medical Doctor Association. Combined diagnosis and treatment guidelines for metabolic syndrome[J]. World Traditional Chinese Medicine, 2023, 18(22): 3157-3166. (In Chinese), articleTitle=Combined diagnosis and treatment guidelines for metabolic syndrome, refAbstract=null), Reference(id=1241057511382511634, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=Lin Z, Sun LN, journalName=Frontiers in Pharmacology, refType=null, unstructuredReference=Lin Z, Sun LN. Research advances in the therapy of metabolic syndrome[J]. Frontiers in Pharmacology, 2024, 15: 1364881., articleTitle=Research advances in the therapy of metabolic syndrome, refAbstract=null), Reference(id=1241057511525117977, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=4, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Chen YF, Xu W, Zhang W, journalName=Cell Reports Medicine, refType=null, unstructuredReference=Chen YF, Xu W, Zhang W, et al. Plasma metabolic fingerprints for large-scale screening and personalized risk stratification of metabolic syndrome[J]. Cell Reports Medicine, 2023, 4(7): 101109., articleTitle=Plasma metabolic fingerprints for large-scale screening and personalized risk stratification of metabolic syndrome, refAbstract=null), Reference(id=1241057511638364192, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2011, volume=26, issue=3, pageStart=32, pageEnd=38, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=方匡南, 吴见彬, 朱建平, journalName=统计与信息论坛, refType=null, unstructuredReference=方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛2011,26(3):32-38., articleTitle=随机森林方法研究综述, refAbstract=null), Reference(id=1241057511755804717, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2011, volume=26, issue=3, pageStart=32, pageEnd=38, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Fang KN, Wu JB, Zhu JP, journalName=Statistics & Information Forum, refType=null, unstructuredReference=Fang KN, Wu JB, Zhu JP, et al.A review of stochastic forest methods[J]. Statistics & Information Forum, 2011, 26(3): 32-38. (In Chinese), articleTitle=A review of stochastic forest methods, refAbstract=null), Reference(id=1241057511877439539, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=1, pageStart=3274, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Zhang YZ, Wu HY, Ma RW, journalName=Scientific Reports, refType=null, unstructuredReference=Zhang YZ, Wu HY, Ma RW, et al. Machine Learning-Based predictive model for adolescentmetabolic syndrome: utilizing data from NHANES 2007-2016[J]. Scientific Reports, 2025, 15(1): 3274., articleTitle=Machine Learning-Based predictive model for adolescentmetabolic syndrome: utilizing data from NHANES 2007-2016, refAbstract=null), Reference(id=1241057511961325626, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=17, issue=null, pageStart=2041, pageEnd=2052, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Ma YT, Li YY, Zhang ZF, journalName=Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy, refType=null, unstructuredReference=Ma YT, Li YY, Zhang ZF, et al. Establishment of a risk prediction model for metabolic syndrome in high altitude areas in Qinghai Province, China: A cross-sectional study[J]. Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy, 2024, 17: 2041-2052., articleTitle=Establishment of a risk prediction model for metabolic syndrome in high altitude areas in Qinghai Province, China: A cross-sectional study, refAbstract=null), Reference(id=1241057512074571844, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=6, pageStart=975, pageEnd=980, 991, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=张骥, 周婕, 吴延莉, journalName=现代预防医学, refType=null, unstructuredReference=张骥,周婕,吴延莉,等.基于贵州省人群队列的代谢综合征发病风险和影响因素分析[J].现代预防医学2022,49(6):975-980, 991., articleTitle=基于贵州省人群队列的代谢综合征发病风险和影响因素分析, refAbstract=null), Reference(id=1241057512179429450, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=6, pageStart=975, pageEnd=980, 991, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Zhang J, Zhou J, Wu YL, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Zhang J, Zhou J, Wu YL, et al. Analysis of risk and influencing factors of metabolic syndrome in the population cohort of Guizhou Province[J]. Modern Preventive Medicine, 2022, 49(6): 975-980, 991. (In Chinese), articleTitle=Analysis of risk and influencing factors of metabolic syndrome in the population cohort of Guizhou Province, refAbstract=null), Reference(id=1241057512288481358, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=4, pageStart=292, pageEnd=344, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=中华医学会糖尿病分会, journalName=中国实用内科杂志, refType=null, unstructuredReference=中华医学会糖尿病分会.中国2型糖尿病防治指南(2017年版)[J].中国实用内科杂志2018,38(4):292-344., articleTitle=中国2型糖尿病防治指南(2017年版), refAbstract=null), Reference(id=1241057512380756053, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=4, pageStart=292, pageEnd=344, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Chinese Diabetes Society, journalName=Chinese Journal of Practical Internal Medicine, refType=null, unstructuredReference=Chinese Diabetes Society. Chinese Guidelines for the prevention and treatment of type 2 diabetes mellitus (2017 edition) [J]. Chinese Journal of Practical Internal Medicine, 2018, 38(4): 292-344. (In Chinese), articleTitle=Chinese Guidelines for the prevention and treatment of type 2 diabetes mellitus (2017 edition), refAbstract=null), Reference(id=1241057512464642140, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=2, pageStart=281, pageEnd=283, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=陈诚, 田青, 李俊, journalName=中国卫生统计, refType=null, unstructuredReference=陈诚,田青,李俊,等.职工代谢综合征患病情况及其影响因素[J].中国卫生统计2024,41(2):281-283., articleTitle=职工代谢综合征患病情况及其影响因素, refAbstract=null), Reference(id=1241057512540139620, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=2, pageStart=281, pageEnd=283, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=Chen C, Tian Q, Li J, journalName=Chinese Journal of Health Statistics, refType=null, unstructuredReference=Chen C, Tian Q, Li J, et al.Prevalence of metabolic syndrome and its influencing factors in workers[J]. Chinese Journal of Health Statistics, 2024, 41(2): 281-283. (In Chinese), articleTitle=Prevalence of metabolic syndrome and its influencing factors in workers, refAbstract=null), Reference(id=1241057512636608619, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Xie QY, Wang MW, Hu ZY, journalName=Frontiers in Public Health, refType=null, unstructuredReference=Xie QY, Wang MW, Hu ZY, et al. Screening the influence of biomarkers for metabolic syndrome in occupationalpopulation based on the lasso algorithm[J]. Frontiers in Public Health, 2021, 9: 743731., articleTitle=Screening the influence of biomarkers for metabolic syndrome in occupationalpopulation based on the lasso algorithm, refAbstract=null), Reference(id=1241057512758243444, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2021, volume=24, issue=19, pageStart=2423, pageEnd=2427, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=刘峰, 夏国宝, 马官慧, journalName=中国全科医学, refType=null, unstructuredReference=刘峰,夏国宝,马官慧,等.北京市某区4 916例医护人员与教职工常见慢性病风险评估结果分析[J].中国全科医学2021,24(19):2423-2427., articleTitle=北京市某区4 916例医护人员与教职工常见慢性病风险评估结果分析, refAbstract=null), Reference(id=1241057512896655482, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2021, volume=24, issue=19, pageStart=2423, pageEnd=2427, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Liu F, Xia GB, Ma GH, journalName=Chinese General Practice, refType=null, unstructuredReference=Liu F, Xia GB, Ma GH, et al.Analysis of risk assessment results of common chronic diseases in 4,916 medical staff and faculty members in a district of Beijing[J]. Chinese General Practice, 2021, 24(19): 2423-2427. (In Chinese), articleTitle=Analysis of risk assessment results of common chronic diseases in 4,916 medical staff and faculty members in a district of Beijing, refAbstract=null), Reference(id=1241057513043456129, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=25, issue=1, pageStart=502, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=Bauer J, Hegewald J, Rossnagel K, journalName=BMC Public Health, refType=null, unstructuredReference=Bauer J, Hegewald J, Rossnagel K, et al. Incidence of type 2 diabetes and metabolic syndrome by Occupation - 10-Year follow-up of the Gutenberg Health Study[J]. BMC Public Health, 2025, 25(1): 502., articleTitle=Incidence of type 2 diabetes and metabolic syndrome by Occupation - 10-Year follow-up of the Gutenberg Health Study, refAbstract=null), Reference(id=1241057513219616906, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=13, pageStart=2325, pageEnd=2330, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=张梅, 李梦启, 普惠婕, journalName=现代预防医学, refType=null, unstructuredReference=张梅,李梦启,普惠婕,等.对比分析彝族和汉族人群TyG-BMI在高血压与代谢综合征的中介作用[J].现代预防医学2024,51(13):2325-2330., articleTitle=对比分析彝族和汉族人群TyG-BMI在高血压与代谢综合征的中介作用, refAbstract=null), Reference(id=1241057513362223245, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=13, pageStart=2325, pageEnd=2330, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=Zhang M, Li MQ, Pu HJ, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Zhang M, Li MQ, Pu HJ, et al. Comparative analysis of the mediating role of TyG-BMI in hypertension and metabolic syndrome between Yi and Han ethnic groups[J]. Modern Preventive Medicine, 2024, 51(13): 2325-2330. (In Chinese), articleTitle=Comparative analysis of the mediating role of TyG-BMI in hypertension and metabolic syndrome between Yi and Han ethnic groups, refAbstract=null), Reference(id=1241057513475469461, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=5, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=Khan UI, Khan SF, Qureshi A, journalName=PLOS Global Public Health, refType=null, unstructuredReference=Khan UI, Khan SF, Qureshi A. Prevalence of metabolic syndrome and its association with cardiovascular disease risk and common risk factors amongst healthcare workers in Pakistan[J]. PLOS Global Public Health, 2025, 5(3): e0004135., articleTitle=Prevalence of metabolic syndrome and its association with cardiovascular disease risk and common risk factors amongst healthcare workers in Pakistan, refAbstract=null), Reference(id=1241057513601298589, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=Park SJ, Kim YN, Oh BK, journalName=Scientific Reports, refType=null, unstructuredReference=Park SJ, Kim YN, Oh BK, et al. Risk factors for metabolic syndrome in the premetabolic state assessed using hierarchical clustering study in a health screening group[J]. Scientific Reports, 2024, 14(1): 31169., articleTitle=Risk factors for metabolic syndrome in the premetabolic state assessed using hierarchical clustering study in a health screening group, refAbstract=null), Reference(id=1241057513701961891, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=6, pageStart=802, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=Ye BJ, journalName=Healthcare, refType=null, unstructuredReference=Ye BJ. Association betweenshift work and metabolic syndrome: A 4-year retrospective cohort study[J]. Healthcare, 2023, 11(6): 802., articleTitle=Association betweenshift work and metabolic syndrome: A 4-year retrospective cohort study, refAbstract=null), Reference(id=1241057513911677099, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=1, pageStart=10, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=Xuan YY, He FF, Liu Q, journalName=Scientific Reports, refType=null, unstructuredReference=Xuan YY, He FF, Liu Q, et al. Elevated GGT to HDL ratio as a marker for the risk of NAFLD and liver fibrosis[J]. Scientific Reports, 2025, 15(1): 10., articleTitle=Elevated GGT to HDL ratio as a marker for the risk of NAFLD and liver fibrosis, refAbstract=null), Reference(id=1241057513991368879, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=32, authorNames=Sun JH, Han KQ, Xu M, journalName=Frontiers in Physiology, refType=null, unstructuredReference=Sun JH, Han KQ, Xu M, et al. Blood viscosity in subjects with type 2 diabetes mellitus: roles of hyperglycemia and elevated plasma fibrinogen[J]. Frontiers in Physiology, 2022, 13: 827428., articleTitle=Blood viscosity in subjects with type 2 diabetes mellitus: roles of hyperglycemia and elevated plasma fibrinogen, refAbstract=null), Reference(id=1241057514045894834, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=5, pageStart=60, pageEnd=66, url=null, language=null, rfNumber=[24], rfOrder=33, authorNames=马彦菁, 顾燕芳, journalName=中国妇幼卫生杂志, refType=null, unstructuredReference=马彦菁,顾燕芳.围绝经期与代谢综合征的相关性研究现况[J].中国妇幼卫生杂志2024,15(5):60-66., articleTitle=围绝经期与代谢综合征的相关性研究现况, refAbstract=null), Reference(id=1241057514192695482, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=5, pageStart=60, pageEnd=66, url=null, language=null, rfNumber=[24], rfOrder=34, authorNames=Ma YJ, Gu YF, journalName=Chinese Journal of Women and Children Health, refType=null, unstructuredReference=Ma YJ, Gu YF. Advances in research on the correlation between perimenopause and metabolic syndrome[J]. Chinese Journal of Women and Children Health, 2024, 15(5): 60-66. (In Chinese), articleTitle=Advances in research on the correlation between perimenopause and metabolic syndrome, refAbstract=null)], funds=[Fund(id=1241057509507658639, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, awardId=SJCX24_1556, language=CN, fundingSource=江苏省研究生科研与实践创新项目(SJCX24_1556), fundOrder=null, country=null), Fund(id=1241057509612516250, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, awardId=2024178, language=CN, fundingSource=中国铁路上海局集团有限公司科研计划(2024178), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241057504633876978, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=1., ext=[AuthorCompanyExt(id=1241057504638071284, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China), AuthorCompanyExt(id=1241057504646459892, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504633876978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.徐州医科大学公共卫生学院,江苏 徐州 221004)]), AuthorCompany(id=1241057504713568762, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, xref=2., ext=[AuthorCompanyExt(id=1241057504721957370, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, companyId=1241057504713568762, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国铁路上海局集团有限公司上海铁路疾病预防控制所)])], figs=[ArticleFig(id=1241057508215812909, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, label=Fig.1, caption=ROC curves for the training and validation sets, figureFileSmall=cp3+Zxh2Yvk0eujeEEb3fg==, figureFileBig=iOMOtzmD3I3kHnGY1caJVw==, tableContent=null), ArticleFig(id=1241057508350030646, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, label=图1, caption=训练集和验证集ROC曲线, figureFileSmall=cp3+Zxh2Yvk0eujeEEb3fg==, figureFileBig=iOMOtzmD3I3kHnGY1caJVw==, tableContent=null), ArticleFig(id=1241057508480054078, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, label=Fig.2, caption=Variance analysis of random survival forest, figureFileSmall=mwd3zN4QOZiMAWWt99625A==, figureFileBig=c0beOTfcRkbGbuAOJK+W+Q==, tableContent=null), ArticleFig(id=1241057508584911684, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, label=图2, caption=随机生存森林变量重要性分析, figureFileSmall=mwd3zN4QOZiMAWWt99625A==, figureFileBig=c0beOTfcRkbGbuAOJK+W+Q==, tableContent=null), ArticleFig(id=1241057508710740817, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, label=Table 1, caption=

Comparison of the general data between the metabolic syndrome group and the non-metabolic syndrome groups[n(%)/$\bar{x} \pm s$

, figureFileSmall=null, figureFileBig=null, tableContent=
变量非MetS组(n=13 561)MetS组(n=3 525)t/Z/χ2P
性别,n(%)<0.01
9 424(69.49)3 427(97.30)
4 137(30.51)98(2.70)
年龄(岁)34.75±9.7042.95±10.9730.430.01
体重(kg)67.87±11.4379.72±10.9756.26<0.01
身高(cm)1.71(1.65,1.75)1.70(1.65,1.75)19.94<0.01
SBP(mmHg)120.64±14.16131.70±14.7840.920.78
DBP(mmHg)75.82±10.3783.63±10.3839.81<0.01
FPG(mmHg)5.11±0.785.51±1.1823.76<0.01
TG(mmol/L)1.37±1.062.20±1.5736.83<0.01
TC(mmol/L)4.61±0.884.91±0.9417.63<0.01
HDL-C(mmol/L)1.41±0.331.25±0.28-26.34<0.01
LDL-C(mmol/L)2.58±0.742.85±0.8118.83<0.01
HGB(g/L)146.89±18.10154.75±16.6223.36<0.01
RBC(×1012/L)4.87±0.485.08±0.3924.81<0.01
WBC(×109/L)6.26±1.576.89±1.6721.01<0.01
ALT(U/L)22.72±17.1831.15±20.8324.78<0.01
GGT(U/L)26.53±20.5442.86±28.7138.43<0.01
STB(μmol/L)13.96±6.0313.97±5.880.110.45
TP(g/L)73.69±4.4773.34±4.37-4.140.83
ALB(g/L)46.10±3.1345.87±3.15-3.760.56
UA(μmol/L)322.37±88.81368.58±90.1027.440.25
CR(μmol/L)72.11±33.2678.41±40.579.540.02
工龄(年)20.34±11.1926.55±10.3129.87<0.01
吸烟,n(%)<0.01
4 723(34.83)1 988(56.40)
8 838(65.17)1 537(43.60)
饮酒,n(%)393.47<0.01
6 178(45.56)954(27.06)
7 383(54.44)2 571(72.94)
辛辣饮食,n(%)0.010.91
7 816(57.63)2 028(57.53)
5 745(42.37)1 497(42.47)
婚姻状况,n(%)88.92<0.01
未婚2 425(17.88)397(11.26)
已婚11 136(82.12)3 128(88.4)
文化程度,n(%)549.58<0.01
初中及以下683(5.04)345(9.79)
高中/中专4 557(33.60)1 761(49.96)
本科/大专8 172(60.26)1 410(40.11)
硕士及以上140(1.03)9(0.26)
工作班制,n(%)31.37<0.01
长白班5 389(39.74)1 310(37.16)
夜班2 413(17.79)547(15.52)
两班倒3 223(23.77)894(25.36)
其他2 536(18.70)774(21.96)
), ArticleFig(id=1241057508937233250, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, label=表1, caption=

代谢综合征组和非代谢综合征组一般资料比较[n(%)或$\bar{x} \pm s$

, figureFileSmall=null, figureFileBig=null, tableContent=
变量非MetS组(n=13 561)MetS组(n=3 525)t/Z/χ2P
性别,n(%)<0.01
9 424(69.49)3 427(97.30)
4 137(30.51)98(2.70)
年龄(岁)34.75±9.7042.95±10.9730.430.01
体重(kg)67.87±11.4379.72±10.9756.26<0.01
身高(cm)1.71(1.65,1.75)1.70(1.65,1.75)19.94<0.01
SBP(mmHg)120.64±14.16131.70±14.7840.920.78
DBP(mmHg)75.82±10.3783.63±10.3839.81<0.01
FPG(mmHg)5.11±0.785.51±1.1823.76<0.01
TG(mmol/L)1.37±1.062.20±1.5736.83<0.01
TC(mmol/L)4.61±0.884.91±0.9417.63<0.01
HDL-C(mmol/L)1.41±0.331.25±0.28-26.34<0.01
LDL-C(mmol/L)2.58±0.742.85±0.8118.83<0.01
HGB(g/L)146.89±18.10154.75±16.6223.36<0.01
RBC(×1012/L)4.87±0.485.08±0.3924.81<0.01
WBC(×109/L)6.26±1.576.89±1.6721.01<0.01
ALT(U/L)22.72±17.1831.15±20.8324.78<0.01
GGT(U/L)26.53±20.5442.86±28.7138.43<0.01
STB(μmol/L)13.96±6.0313.97±5.880.110.45
TP(g/L)73.69±4.4773.34±4.37-4.140.83
ALB(g/L)46.10±3.1345.87±3.15-3.760.56
UA(μmol/L)322.37±88.81368.58±90.1027.440.25
CR(μmol/L)72.11±33.2678.41±40.579.540.02
工龄(年)20.34±11.1926.55±10.3129.87<0.01
吸烟,n(%)<0.01
4 723(34.83)1 988(56.40)
8 838(65.17)1 537(43.60)
饮酒,n(%)393.47<0.01
6 178(45.56)954(27.06)
7 383(54.44)2 571(72.94)
辛辣饮食,n(%)0.010.91
7 816(57.63)2 028(57.53)
5 745(42.37)1 497(42.47)
婚姻状况,n(%)88.92<0.01
未婚2 425(17.88)397(11.26)
已婚11 136(82.12)3 128(88.4)
文化程度,n(%)549.58<0.01
初中及以下683(5.04)345(9.79)
高中/中专4 557(33.60)1 761(49.96)
本科/大专8 172(60.26)1 410(40.11)
硕士及以上140(1.03)9(0.26)
工作班制,n(%)31.37<0.01
长白班5 389(39.74)1 310(37.16)
夜班2 413(17.79)547(15.52)
两班倒3 223(23.77)894(25.36)
其他2 536(18.70)774(21.96)
), ArticleFig(id=1241057509180502893, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=EN, label=Table 2, caption=

Three models prediction and evaluation indicators

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集模型AUCC-index灵敏度特异度准确度F1分数
训练集Cox0.8700.8530.6120.9330.6780.751
RSF0.9380.9350.9680.7420.7880.839
GBM0.8910.8430.6280.9940.7030.749
验证集Cox0.8660.8490.6120.9280.6790.751
RSF0.9370.9670.9650.7260.7760.828
GBM0.8900.8490.6110.9230.6760.749
), ArticleFig(id=1241057509289554808, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241036244667396393, language=CN, label=表2, caption=

三种模型预测评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集模型AUCC-index灵敏度特异度准确度F1分数
训练集Cox0.8700.8530.6120.9330.6780.751
RSF0.9380.9350.9680.7420.7880.839
GBM0.8910.8430.6280.9940.7030.749
验证集Cox0.8660.8490.6120.9280.6790.751
RSF0.9370.9670.9650.7260.7760.828
GBM0.8900.8490.6110.9230.6760.749
)], attaches=null, journal=Journal(id=1227664546253402114, delFlag=0, nameCn=现代预防医学, nameEn=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, issn=1003-8507, eissn=null, cn=51-1365/R, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=IeiuPXEZi6AA+k0VfvoiOQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Modern Preventive Medicine, journalRemark=null, publicationField=null, createdTime=1770627636734, updatedTime=1770628902248, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=null, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=IeiuPXEZi6AA+k0VfvoiOQ==, picEn=/9iTl8/ndms4tBz1fL28Pg==, jcr=null, cjcr=null, exts=[JournalExt(id=1227669854342280188, language=CN, name=现代预防医学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770628902278, updatedTime=1770628902278, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1227669854396806141, language=EN, name=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770628902291, updatedTime=1770628902291, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227665162245664772, websiteList=[Website(id=1227687234141352800, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/CN, language=CN, createTime=1770633045945, createBy=18614031015, updateTime=1770633090526, updateBy=18614031015, name=现代预防医学-中文, tplId=1146099689490845704, title=现代预防医学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687735088051072, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=articleTextType, value=kx, createTime=1770633165380, updateTime=1770633165380, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735071273853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=banner, value=null, createTime=1770633165376, updateTime=1770633165376, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735113216899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=grayFlag, value=0, createTime=1770633165386, updateTime=1770633165386, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735062885244, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633165374, updateTime=1770633165374, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735125799813, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=minRunFlag, value=0, createTime=1770633165389, updateTime=1770633165389, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735083856767, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic, createTime=1770633165379, updateTime=1770633165379, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735121605508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=silenceFlag, value=0, createTime=1770633165388, updateTime=1770633165388, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735079662462, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770633165378, updateTime=1770633165378, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735096439681, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeColor, value=null, createTime=1770633165382, updateTime=1770633165382, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735104828290, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeStyle, value=null, createTime=1770633165384, updateTime=1770633165384, creator=18614031015, updator=18614031015)]), Website(id=1227687234338485094, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/EN, language=EN, createTime=1770633045992, createBy=18614031015, updateTime=1770633115374, updateBy=18614031015, name=现代预防医学-英文, tplId=1146101810881728533, title=Modern Preventive Medicine, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687709129507332, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=articleTextType, value=kx, createTime=1770633159191, updateTime=1770633159191, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709108535809, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=banner, value=null, createTime=1770633159186, updateTime=1770633159186, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709167256071, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=grayFlag, value=0, createTime=1770633159200, updateTime=1770633159200, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709095952896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633159183, updateTime=1770633159183, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709179838985, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=minRunFlag, value=0, createTime=1770633159203, updateTime=1770633159203, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709121118723, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic, createTime=1770633159189, updateTime=1770633159189, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709171450376, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=silenceFlag, value=0, createTime=1770633159201, updateTime=1770633159201, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709112730114, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770633159187, updateTime=1770633159187, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709133701637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeColor, value=null, createTime=1770633159192, updateTime=1770633159192, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709154673158, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeStyle, value=null, createTime=1770633159197, updateTime=1770633159197, creator=18614031015, updator=18614031015)])], journalTitle=现代预防医学, weixinUrl=null, journalUrl=http://xdyfyxzz.paperopen.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Modern Preventive Medicine, journalPhotoCn=IeiuPXEZi6AA+k0VfvoiOQ==, journalPhotoEn=/9iTl8/ndms4tBz1fL28Pg==, journalFirstLetter=M, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202503082, detailUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202503082, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/PDF/10.20043/j.cnki.MPM.202503082, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/PDF/10.20043/j.cnki.MPM.202503082, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于机器学习算法构建铁路职工代谢综合征预测模型
收藏切换
PDF下载
吴琼 1 , 卫雨甜 1 , 孙伟恒 1 , 肖立顺 1 , 丛晓娜 2 , 胡斌 1
现代预防医学 | 流行病与统计方法 2025,52(16): 2894-2899
收起
收藏切换
现代预防医学 | 流行病与统计方法 2025, 52(16): 2894-2899
基于机器学习算法构建铁路职工代谢综合征预测模型
全屏
吴琼1, 卫雨甜1, 孙伟恒1, 肖立顺1, 丛晓娜2, 胡斌1
作者信息
  • 1.徐州医科大学公共卫生学院,江苏 徐州 221004
  • 2.中国铁路上海局集团有限公司上海铁路疾病预防控制所
  • 吴琼(2001—),女,硕士在读,研究方向:公共卫生

通讯作者:

胡斌,E-mail:
Prediction model of metabolic syndrome for railway workers based on machine learning algorithm
Qiong WU1, Yu-tian WEI1, Wei-heng SUN1, Li-shun XIAO1, Xiao-na CONG2, Bin HU1
Affiliations
  • School of Public Health, Xuzhou Medical University, Xuzhou, Jiangsu 221004, China
出版时间: 2025-08-25 doi: 10.20043/j.cnki.MPM.202503082
文章导航
收藏切换
目的

基于机器学习算法(Machine Learning,ML)构建铁路职工代谢综合征(Metabolic Syndrome,MetS)预测模型并对预测效果进行评价。

方法

以是否出现代谢综合征为结局变量,以人口学特征和生化指标为预测变量,采用单因素分析筛选出预测指标。将研究对象按7:3的比例随机划分成训练集和测试集,分别采用Cox比例风险回归、随机生存森林(Random Survival Forest,RSF)和梯度提升机(Gradient Boosting Machine,GBM)建立代谢综合征预测模型,采用受试者工作特征曲线下面积(Area under curve,AUC)、一致性指标(C-index)、灵敏度、特异度、准确度、F1分数评估模型性能。借助shiny程序包绘制风险计算器。

结果

本研究共纳入17 087名研究对象,共采集28项指标,单因素分析筛选出22个有统计学意义的指标。在训练集中,Cox、RSF和GBM模型构建的预测模型AUC分别为0.870、0.938和0.891;C-index分别为0.853、0.935和0.843;灵敏度分别为0.612、0.968和0.628;特异度分别为0.933、0.742和0.994;准确度分别为0.678、0.788和0.703;F1分数分别为0.751、0.839和0.749。

结论

RSF模型在预测铁路员工代谢综合征方面表现优于Cox模型和GBM模型,为早期识别代谢综合征提供了科学依据,并有助于推动一级预防措施的实施。

随机生存森林  /  Cox回归模型  /  梯度提升机  /  代谢综合征  /  机器学习
Objective

To construct a prediction model for metabolic syndrome (Metabolic Syndrome, MetS) in railway employees based on machine learning algorithms (Machine Learning, ML) and evaluate the prediction performance.

Methods

The time to the onset of metabolic syndrome was used as the outcome variable, with demographic characteristics and biochemical indicators as predictive variables. Univariate analysis was conducted to select predictive indicators. The study subjects were randomly divided into a training set and a test set in a 7:3 ratio. Cox proportional hazards regression, Random Forest (Random Survival Forest, RSF), and Gradient Boosting Machine (Gradient Boosting Machine, GBM) were used to build metabolic syndrome prediction models. Model performance was assessed using the area under the receiver operating characteristic curve (Area under curve, AUC), concordance index (C-index), sensitivity, specificity, accuracy, and F1 score. A risk calculator was created using the shiny package.

Results

This study included 17 087 subjects and collected 28 indicators. Univariate analysis identified 22 statistically significant indicators. In the training set, the areas under the curve (area under the curve, AUC) of the prediction models constructed by Cox, RSF, and GBM were 0.870,0.938, and 0.891, respectively; C-index values were 0.853,0.935, and 0.843; sensitivity was 0.612,0.968, and 0.628; specificity was 0.933,0.742, and 0.994; accuracy was 0.678,0.788, and 0.703; F1 scores were 0.751,0.839, and 0.749.

Conclusion

The RSF model outperformed the Cox model and the GBM model in predicting metabolic syndrome among railway employees, providing a scientific basis for early identification of metabolic syndrome and aiding in the implementation of primary prevention measures.

Random survival forest  /  Cox regression model  /  Gradient Boosting Machine  /  Metabolic syndrome  /  Machine learning
吴琼, 卫雨甜, 孙伟恒, 肖立顺, 丛晓娜, 胡斌. 基于机器学习算法构建铁路职工代谢综合征预测模型. 现代预防医学, 2025 , 52 (16) : 2894 -2899 . DOI: 10.20043/j.cnki.MPM.202503082
Qiong WU, Yu-tian WEI, Wei-heng SUN, Li-shun XIAO, Xiao-na CONG, Bin HU. Prediction model of metabolic syndrome for railway workers based on machine learning algorithm[J]. Modern Preventive Medicine, 2025 , 52 (16) : 2894 -2899 . DOI: 10.20043/j.cnki.MPM.202503082
近年来,我国铁路事业发展迅猛,铁路职工数量不断增加,以适应铁路网络的扩展和运输需求的增长。有研究表明,铁路职工由于其特殊的工作环境,如夜班轮班、高强度工作、不规律的生活习惯等,更容易受到代谢综合征(Metabolic Syndrome,MetS)的威胁[1-3]。代谢综合征是一组包括腹部肥胖、高血压、高血糖、异常血脂水平等异常的病理状态,这些因素共同增加了心血管疾病和Ⅱ型糖尿病的风险[4-5]。2023年《代谢综合征病证结合诊疗指南》报告,我国20岁及以上人群MetS患病率为31.1%[6]。MetS已成为全球关注的严重公共卫生问题[7]。此外,MetS的发病机制复杂,早期患者一般没有明显的临床症状,难以检测,容易被忽视[8]
传统的MetS风险预测多依赖于Cox比例风险回归模型,但该方法在处理非线性关系和复杂交互效应时存在局限性。近年来,机器学习(Machine Learning,ML)算法在医学预测模型中展现出显著优势,能够捕捉复杂的变量关系并提高预测精度[9]。然而,现有研究多基于普通人群[10-12],针对铁路职工这一特定群体的MetS风险预测研究仍较为缺乏。本研究旨在使用机器学习技术和人口健康数据实现MetS的早期识别,并探讨其发病影响因素。本研究构建了随机生存森林(Random Survival Forest,RSF)、梯度提升机(Gradient Boosting Machine,GBM)和Cox回归模型,并对三种模型进行了综合比较和评价,最终RSF表现最优。及时识别MetS高危人群,有利于早期干预,从而为该群体MetS的早期识别提供科学的理论基础,并推动一级预防措施的实施。
本研究为随访研究,基线数据收集于2019年,随访周期为5年(2019-2023年),研究对象在该中心的第一次体检数据视为基线数据,随后的每年体检数据为随访数据。在研究过程中,严格遵循既定的纳入与排除标准,对所有初始纳入人员展开为期五年的随访,随访截止日期为2023年12月31日。经长期跟踪观察与数据整理,最终确定符合研究要求的研究对象共17 087名,这些研究对象均具备完整的资料,且顺利完成了五年随访流程,为后续研究提供了可靠的数据基础。
纳入标准:(1)完成基线及随访体检;(2)基线无MetS;(3)基线代谢指标均处于正常范围内。排除标准:(1)MetS相关诊断指标缺失者;(2)MetS检测结果反复不一致的人群。(3)工龄<1年。本研究已经过徐州医科大学伦理委员会批准(XZHMU-2023626),所有研究对象均知情同意。
本研究收集了28项人口学特征、实验室指标及生活方式数据,具体包括:年龄(岁)、性别、身高(cm)、体重(kg)、工龄(年)、婚姻状况、文化程度、工作班制、家庭人均月收入(元/人)、收缩压(SBP,mmHg)、舒张压(DBP,mmHg)、空腹血糖(FPG,mmol/L)、甘油三酯(TG,mmol/L)、总胆固醇(TC,mmol/L)、高密度脂蛋白(HDL-C,mmol/L)、低密度脂蛋白(LDL-C,mmol/L)、血红蛋白(HGB,g/L)、红细胞计数(RBC,×1012/L)、白细胞计数(WBC,×109/L)、丙氨酸氨基转移酶(ALT,U/L)、谷氨酰转肽酶(GGT,U/L)、总蛋白(TP,g/L)、总胆红素(STB,μmol/L)、白蛋白(ALB,g/L)、尿酸(UA,μmol/L)、肌酐(CR,μmol/L)、吸烟史(是/否)、饮酒习惯(是/否)、辛辣饮食频率。
根据《中国Ⅱ型糖尿病防治指南(2017年版)》[13]的标准,符合3项及以上者定义为MetS:(1)超重和(或)肥胖:BMI≥25 kg/m2;(2)高血糖:FPG≥6.1 mmol/L(110 mg/dl)及(或)2hFPG≥7.8 mmol/L(140 mg/dl),及(或)已确诊为糖尿病并治疗者;(3)高血压:SBP≥140/90 mmHg及(或)已确认为高血压并治疗者(4)血脂紊乱:空腹血浆TG≥1.7 mmol/L(150 mg/dl),及(或)空腹HDL-C<0.9 mmol/L(35 mg/dl)(男)或<1.0 mmol/L(39 mg/dl)(女)。
采用SPSS 26.0和R 4.4.1软件进行数据处理。定量资料采用平均数±标准差表示,定性资料采用频数及构成比表示,即n(%)。定量资料的差异性比较采用t检验或Mann-Whitney U检验分析,定性资料采用χ2检验分析。使用caret包构建Cox、RSF、GBM模型,采用AUC、C-index、灵敏度、特异度、准确度、F1分数评价模型。借助shiny程序包绘制MetS风险计算器。检验水准α=0.05。
本研究最终共纳入17 087名研究对象,平均年龄为43岁,其中,男性12 851名,女性4 235名。发生MetS的人数为3 525人。MetS组与非MetS组基线资料比较见表1。MetS组与非MetS组SBP、STB、TP、ALB、UA和辛辣饮食比较,差异无统计学意义(P>0.05)。
为了全面评估MetS风险预测模型的性能,并筛选出最优预测模型,将研究对象按7∶3的比例随机分为两组。表2显示了训练集(n=11 981)和验证集(n=5 105)中研究对象的基线特征。结果显示,训练集和验证集在基线信息和生化指标等方面差异均无统计学意义。经过验证,训练集和验证集在关键特征上的分布相似,均衡性较好。
本研究建立Cox回归、RSF和GBM模型,将具有统计学意义的22个变量纳入模型进行训练,分别绘制训练集和验证集ROC曲线,比较模型AUC值,AUC是衡量模型区分两个类别能力的指标,AUC值越高,模型的预测性能通常被认为越好。三个模型在训练集和验证集上的AUC值非常接近,这表明模型的稳定性较好。在训练集中,Cox回归、RSF和GBM模型的AUC值分别为0.870、0.938和0.891,验证集的AUC值分别为0.877、0.939和0.895。RSF模型在训练集和验证集上的表现都优于Cox和GBM模型,测性能更较好。此外,在训练集中,Cox回归模型、RSF模型和GBM模型C-index分别为0.853、0.935和0.843;验证集的C-index分别为0.849、0.967、0.849。C-index的范围从0到1,其中1表示完美的预测准确性,0.5以下表示随机预测,三个模型的C-index均大于0.75,表明区分力相对较好[11]。F1分数的取值范围为0~1,值越接近1,表示模型的性能越好,在训练集中和验证集中,RSF模型的F1分数均比其他两个模型高,分别为0.839和0.828。以上结果表明,RSF模型比Cox回归模型和GBM模型更稳定可靠。具体结果见表2图1
为了进一步深入探究影响MetS风险的关键预测因子,本研究运用RSF模型的变量重要性(Variable Importance,VIMP)分析方法。在随机生存森林模型里,VIMP用于衡量各个变量对模型准确度的影响程度,VIMP值越大,意味着该变量对模型的影响越大,其重要性也就越高。在分析过程中,我们基于VIMP值的显著性对变量进行筛选。保留了VIMP值显著高于零的变量,而VIMP值接近零或为负的变量对模型的预测能力贡献有限,因此未被纳入进一步分析。通过RSF模型筛选出的重要变量中,MetS的传统诊断指标表现出显著的预测能力,这一结果与临床诊断标准高度一致,表明模型能够有效捕捉MetS的核心特征。值得注意的是,模型识别出多个与MetS发病密切相关的非传统指标,包括年龄(VIMP=0.050)、GGT(VIMP=0.036)、工龄(VIMP=0.025)、性别(VIMP=0.020)及HGB(VIMP=0.020)(见图2)。这些指标的预测能力提示,MetS的发生也受到生活方式因素和非传统指标的协同调控。
为了进一步表现RSF模型的结果,将RSF模型显示的对预测具有显著意义的6个指标作为预测变量拟合MetS风险计算器(https://w2337975581.shinyapps.io/QQQQ/),通过输入相关信息计算个人未来患MetS的风险比和患病概率,帮助铁路工人了解自身未来患病风险,增强一级预防。以一名体重为55 kg,舒张压88 mmHg,空腹血糖4.4 mmol/L,甘油三酯1.56 mmol/L,谷氨酰转肽酶25 U/L的65岁职工为例,该个体未来患MetS的概率为10%。
代谢综合征作为涉及腹型肥胖、高血压、糖脂代谢紊乱等多因素的复杂临床综合征,其早期筛查和风险评估对职业人群健康管理具有重要意义[14-15]。本研究聚焦长期缺乏关注的铁路职业人群,构建基于机器学习的MetS风险预测模型,并开发可视化风险计算工具,为职业健康干预提供了新策略。与我国20岁及以上人群31.1%的MetS患病率相比[6],本队列20.65%的检出率相对较低,可能与研究对象年龄结构偏中年,60岁以上职工占比较少的职业特性相关。值得注意的是,该数值仍显著高于其他职业人群报告值[16-17],提示铁路职工特有的轮班制、夜间工作等职业暴露可能构成独立风险。这一发现填补了现有研究多聚焦普通人群而忽视职业特异性的空白。
本研究为随访研究,基线数据收集于2019年,随访周期为5年,所有基线参与者均未满足MetS的诊断标准且基线代谢指标均处于正常范围内,基线代谢指标作为连续型变量纳入分析,其水平能反映早期代谢紊乱,具有预测价值。本研究基线指标是独立于随访结果的预测变量,且未患病人群的基线数据与随访诊断在时间维度上严格分离,避免了循环论证风险。
机器学习通过高效处理海量数据、挖掘复杂非线性关系,为疾病预测和诊断提供了全新的解决方案。本研究基于机器学习算法构建了Cox、RSF和GBM三种预测模型,通过系统评估发现:RSF模型在各项指标上均显著优于传统Cox模型和GBM模型,其曲线下面积(0.938)、C-index(0.935)、灵敏度(0.968)等关键指标均达到最优水平,特别是在区分度和校准度方面表现突出。这一结果充分证实了机器学习方法在MetS预测中的优越性,其能够有效捕捉传统统计方法难以识别的复杂特征交互作用。
通过RSF模型的特征重要性分析,我们成功识别出年龄、体重、舒张压、空腹血糖、甘油三酯和γ-谷氨酰转移酶等关键预测因子,这些发现为MetS的早期预警提供了重要的理论依据。目前,国内外研究已发现多种与MetS发病有关的危险因素[18-20]。其中,体质指数、空腹血糖、收缩压、舒张压、甘油三酯,高密度脂蛋白作为MetS诊断相关指标,已被研究证实是MetS的影响因素,本研究结果与之一致。此外,本研究通过RSF模型识别出多个与MetS发病密切相关的非传统指标,包括年龄、γ-谷氨酰转移酶、工龄、性别及血红蛋白,这些指标的预测能力提示MetS的发生除受到诊断指标的影响之外,也受到生活方式因素和非传统指标的协同调控。首先,本研究提示MetS受到年龄与工龄的影响,研究的结果与既往研究一致[21],年龄增长与MetS风险的正相关性反映了机体代谢功能随时间的渐进性衰退,而工龄的独立预测价值提示职业暴露可能通过轮班工作扰乱昼夜节律加速代谢失衡。二者叠加可能形成双重负荷,这为高工龄人群制定代谢评估方案或具有预防价值。其次,既往研究提示γ-谷氨酰转移酶的升高与脂肪肝进展及胰岛素抵抗密切相关,其可能通过介导氧化应激反应促进内脏脂肪蓄积[22]。本结果进一步支持将γ-谷氨酰转移酶纳入代谢风险评估体系,有助于更全面地评估个体的代谢健康状况和疾病风险。同时,血红蛋白水平显示出独立于传统心血管风险因子的预测价值。血红蛋白水平与MetS之间关联的可能机制如下:高血红蛋白水平可增加血液粘度,导致血流减缓,进而使胰岛素、葡萄糖和氧气向组织的输送减少,诱导胰岛素抵抗,而胰岛素抵抗正是MetS的核心发病机制之一[23]。此外,性别差异的显著性提示需建立性别特异性预防策略。女性在绝经前因雌激素保护作用呈现较低风险[24],而职业人群中男性吸烟、饮酒率高、饮食结构不合理等特点,针对青年男性开展代谢健康监测具有必要性。这些非传统指标的协同作用凸显了MetS的多维度致病机制。这提示未来临床实践需突破“体重中心主义”的筛查模式,整合生活方式评估、器官功能指标及血液流变学参数构建综合预测模型。
本研究也有一定不足。首先研究的随访期限相对较短,需要进行更长时间的随访研究,以进一步确认预测模型的可靠性和实用性。其次,本研究所采用的预测指标相对传统,未来应考虑纳入更多新颖且敏感的预测指标,以提高模型的预测能力。
综上所述,本研究通过构建Cox、RSF和GBM模型来预测MetS,并对比分析了这三种模型的预测准确性。结果显示,与Cox和GBM模型相比,RSF模型在预测性能上更为优越,使用这种高度可解释的机器学习方法确定了一些重要的特异性预测因子,可为MetS早期识别提供参考。
  • 江苏省研究生科研与实践创新项目(SJCX24_1556)
  • 中国铁路上海局集团有限公司科研计划(2024178)
参考文献 引证文献
排序方式:
[1]
杜懿涵,陆崇,冯小燕,等.铁路职工夜班工作与代谢综合征的关联性分析[J].现代预防医学2024,51(5):811-816.
Du YH, Lu C, Feng XY, et al. Analysis of the relationship between night shift work and metabolic syndrome in railway workers[J]. Modern Preventive Medicine, 2024, 51(5): 811-816. (In Chinese)
[2]
杨波,冯传腾,于文倩,等.铁路职业人群夜班轮班工作与代谢综合征的关联及中介效应分析[J].现代预防医学2023,50(2):239-244, 262.
Yang B, Feng CT, Yu WQ, et al. Association and mediating effects of night shift work on metabolic syndrome in railway professional workers[J]. Modern Preventive Medicine, 2023, 50(2): 239-244, 262. (In Chinese)
[3]
于跃,白国霞,扎西宗吉,等.西藏中老年人代谢综合征患病现状及危险因素分析[J].现代预防医学2025,52(2):376-380.
Yu Y, Bai GX, Za XZJ, et al. Prevalence and risk factors of metabolic syndrome among middle-aged and elderly People in Tibet[J]. Modern Preventive Medicine, 2025, 52(2): 376-380. (In Chinese)
[4]
Gharipour M, Nezafati PY, Sadeghian L, et al. Precision medicine and metabolic syndrome[J]. ARYA Atherosclerosis, 2022, 18(4): 1-10.
[5]
Fahed G, Aoun L, Bou zerdan M, et al. Metabolic syndrome: updates on pathophysiology and management in 2021[J]. International Journal of Molecular Sciences, 2022, 23(2): 786.
[6]
中国医师协会中西医结合医师分会内分泌与代谢病学专业委员会.代谢综合征病证结合诊疗指南[J].世界中医药2023,18(22):3157-3166.
Endocrinology and Metabolic Diseases Committee of Integrated Traditional Chinese and Western Medicine Branch of Chinese Medical Doctor Association. Combined diagnosis and treatment guidelines for metabolic syndrome[J]. World Traditional Chinese Medicine, 2023, 18(22): 3157-3166. (In Chinese)
[7]
Lin Z, Sun LN. Research advances in the therapy of metabolic syndrome[J]. Frontiers in Pharmacology, 2024, 15: 1364881.
[8]
Chen YF, Xu W, Zhang W, et al. Plasma metabolic fingerprints for large-scale screening and personalized risk stratification of metabolic syndrome[J]. Cell Reports Medicine, 2023, 4(7): 101109.
[9]
方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛2011,26(3):32-38.
Fang KN, Wu JB, Zhu JP, et al.A review of stochastic forest methods[J]. Statistics & Information Forum, 2011, 26(3): 32-38. (In Chinese)
[10]
Zhang YZ, Wu HY, Ma RW, et al. Machine Learning-Based predictive model for adolescentmetabolic syndrome: utilizing data from NHANES 2007-2016[J]. Scientific Reports, 2025, 15(1): 3274.
[11]
Ma YT, Li YY, Zhang ZF, et al. Establishment of a risk prediction model for metabolic syndrome in high altitude areas in Qinghai Province, China: A cross-sectional study[J]. Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy, 2024, 17: 2041-2052.
[12]
张骥,周婕,吴延莉,等.基于贵州省人群队列的代谢综合征发病风险和影响因素分析[J].现代预防医学2022,49(6):975-980, 991.
Zhang J, Zhou J, Wu YL, et al. Analysis of risk and influencing factors of metabolic syndrome in the population cohort of Guizhou Province[J]. Modern Preventive Medicine, 2022, 49(6): 975-980, 991. (In Chinese)
[13]
中华医学会糖尿病分会.中国2型糖尿病防治指南(2017年版)[J].中国实用内科杂志2018,38(4):292-344.
Chinese Diabetes Society. Chinese Guidelines for the prevention and treatment of type 2 diabetes mellitus (2017 edition) [J]. Chinese Journal of Practical Internal Medicine, 2018, 38(4): 292-344. (In Chinese)
[14]
陈诚,田青,李俊,等.职工代谢综合征患病情况及其影响因素[J].中国卫生统计2024,41(2):281-283.
Chen C, Tian Q, Li J, et al.Prevalence of metabolic syndrome and its influencing factors in workers[J]. Chinese Journal of Health Statistics, 2024, 41(2): 281-283. (In Chinese)
[15]
Xie QY, Wang MW, Hu ZY, et al. Screening the influence of biomarkers for metabolic syndrome in occupationalpopulation based on the lasso algorithm[J]. Frontiers in Public Health, 2021, 9: 743731.
[16]
刘峰,夏国宝,马官慧,等.北京市某区4 916例医护人员与教职工常见慢性病风险评估结果分析[J].中国全科医学2021,24(19):2423-2427.
Liu F, Xia GB, Ma GH, et al.Analysis of risk assessment results of common chronic diseases in 4,916 medical staff and faculty members in a district of Beijing[J]. Chinese General Practice, 2021, 24(19): 2423-2427. (In Chinese)
[17]
Bauer J, Hegewald J, Rossnagel K, et al. Incidence of type 2 diabetes and metabolic syndrome by Occupation - 10-Year follow-up of the Gutenberg Health Study[J]. BMC Public Health, 2025, 25(1): 502.
[18]
张梅,李梦启,普惠婕,等.对比分析彝族和汉族人群TyG-BMI在高血压与代谢综合征的中介作用[J].现代预防医学2024,51(13):2325-2330.
Zhang M, Li MQ, Pu HJ, et al. Comparative analysis of the mediating role of TyG-BMI in hypertension and metabolic syndrome between Yi and Han ethnic groups[J]. Modern Preventive Medicine, 2024, 51(13): 2325-2330. (In Chinese)
[19]
Khan UI, Khan SF, Qureshi A. Prevalence of metabolic syndrome and its association with cardiovascular disease risk and common risk factors amongst healthcare workers in Pakistan[J]. PLOS Global Public Health, 2025, 5(3): e0004135.
[20]
Park SJ, Kim YN, Oh BK, et al. Risk factors for metabolic syndrome in the premetabolic state assessed using hierarchical clustering study in a health screening group[J]. Scientific Reports, 2024, 14(1): 31169.
[21]
Ye BJ. Association betweenshift work and metabolic syndrome: A 4-year retrospective cohort study[J]. Healthcare, 2023, 11(6): 802.
[22]
Xuan YY, He FF, Liu Q, et al. Elevated GGT to HDL ratio as a marker for the risk of NAFLD and liver fibrosis[J]. Scientific Reports, 2025, 15(1): 10.
[23]
Sun JH, Han KQ, Xu M, et al. Blood viscosity in subjects with type 2 diabetes mellitus: roles of hyperglycemia and elevated plasma fibrinogen[J]. Frontiers in Physiology, 2022, 13: 827428.
[24]
马彦菁,顾燕芳.围绝经期与代谢综合征的相关性研究现况[J].中国妇幼卫生杂志2024,15(5):60-66.
Ma YJ, Gu YF. Advances in research on the correlation between perimenopause and metabolic syndrome[J]. Chinese Journal of Women and Children Health, 2024, 15(5): 60-66. (In Chinese)
2025年第52卷第16期
PDF下载
43
17
引用本文
BibTeX
文章信息
doi: 10.20043/j.cnki.MPM.202503082
  • 接收时间:2025-03-05
  • 首发时间:2026-03-18
  • 出版时间:2025-08-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-05
基金
江苏省研究生科研与实践创新项目(SJCX24_1556)
中国铁路上海局集团有限公司科研计划(2024178)
作者信息
    1.徐州医科大学公共卫生学院,江苏 徐州 221004
    2.中国铁路上海局集团有限公司上海铁路疾病预防控制所

通讯作者:

胡斌,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202503082
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏