妊娠期糖尿病早孕期相关影响因素及基于早孕期孕妇糖脂相关生化指标与人口学资料的4种机器学习算法构建妊娠期糖尿病预测模型的临床价值  

Analysis of early pregnancy-related influencing factors of gestational diabetes mellitus,and clinical value of building gestational diabetes mellitus prediction model based on four machine learning algorithms of glycolipid-related biochemical indexes and demographic information of pregnant women in early pregnancy

作　　者：李莉[1] 马梅[2] 黄欣欣[3] 杨丹林[1] 潘勉[1] Li Li;Ma Mei;Huang Xinxin;Yang Danlin;Pan Mian(Department of Obstetrics,Fujian Maternity and Child Health Hospital,College of Clinical Medicine for Obstetrics&Gynecology and Pediatrics,Fujian Medical University,Fuzhou 350001,Fujian Province,China;Department of Laboratory Medicine,Fujian Maternity and Child Health Hospital,College of Clinical Medicine for Obstetrics&Gynecology and Pediatrics,Fujian Medical University,Fuzhou 350001,Fujian Province,China;Department of Healthcare,Fujian Maternity and Child Health Hospital,College of Clinical Medicine for Obstetrics&Gynecology and Pediatrics,Fujian Medical University,Fuzhou 350001,Fujian Province,China)

机构地区：[1]福建省妇幼保健院·福建医科大学妇儿临床医学院产科,福州350001 [2]福建省妇幼保健院·福建医科大学妇儿临床医学院检验科,福州350001 [3]福建省妇幼保健院·福建医科大学妇儿临床医学院保健部,福州350001

出　　处：《中华妇幼临床医学杂志（电子版）》2024年第1期105-113,共9页Chinese Journal of Obstetrics & Gynecology and Pediatrics(Electronic Edition)

基　　金：福建省科技厅自然科学基金项目(2021J01406)。

摘　　要：目的探讨妊娠期糖尿病(GDM)的早孕期相关影响因素,以及基于早孕期孕妇糖脂相关生化指标及人口学资料,采用4种机器学习算法构建GDM预测模型的临床价值。方法选择2021年12月至2022年12月在福建省妇幼保健院首次进行产前检查的6257例孕龄为10~13+6孕周孕妇为研究对象。采取回顾性分析法,根据孕妇24~27+6孕周(中孕期)时是否被诊断为GDM,将其分为GDM组(n=1499,GDM孕妇)和非GDM组(n=4758,非GDM孕妇)。采用多因素非条件logistic回归分析法,对孕妇发生GDM的早孕期相关影响因素进行分析。基于早孕期孕妇糖脂相关生化指标和人口学资料(8个变量),采用决策树(DT)、逻辑回归(LR)、随机森林(RF)及极致梯度提升(XGB)4种机器学习算法构建GDM预测模型,并且采用十折交叉验证,评估4种模型的GDM预测性能;并对4种算法构建GDM预测模型的受试者工作特征(ROC)曲线的曲线下面积(AUC)进行比较。本研究经福建省妇幼保健院伦理委员会批准(审批文号:2021KRD018)。所有孕妇签署临床研究知情同意书。结果①多因素非条件logistic回归分析结果显示,孕妇高龄(分娩年龄≥35岁)(OR=1.95,95%CI:1.70~2.24,P<0.001),孕前人体质量指数(BMI)≥18.5~24.0 kg/m^(2)(OR=1.32,95%CI:1.11~1.58,P=0.002),孕前BMI≥24.0~28.0 kg/m^(2)(OR=2.17,95%CI:1.73~2.73,P<0.001),孕前BMI≥28.0 kg/m^(2)(OR=2.53,95%CI:1.70~3.78,P<0.001),早孕期血清载脂蛋白(Apo)B水平升高(OR=3.06,95%CI:2.14~4.37,P<0.001),早孕期血清空腹血糖(FPG)浓度增加(OR=2.08,95%CI:1.79~2.41,P<0.001),均为孕妇发生GDM的早孕期相关独立危险因素。②根据4种分类器的分类结果中特征值大小,采用孕妇年龄、受教育程度及孕前BMI,早孕期血清总胆固醇(TC)、甘油三酯(TG)、ApoA1、ApoB及FPG水平8个变量进行GDM预测模型构建的结果显示:DT、LR、RF、XGB 4种算法建立的GDM预测模型的AUC分别为0.645(95%CI:0.591~0.698)、0.699(95%CI:0.641~0.749)、0.672(95%Objective To investigate the early pregnancy-related influencing factors of gestational diabetes mellitus(GDM),as well as the clinical value of building GDM prediction model based on the glycolipids-related biochemical indexes in early pregnancy and demographic information using four machine learning algorithms.Methods A total of 6257 pregnant women with gestational age of 10 to 13+6 gestational weeks who had their first prenatal examinations in Fujian Maternity and Child Health Hospital from December 2021 to December 2022 were selected for the study.The pregnant women were categorized into the GDM group(n=1499,GDM pregnant women)and the non-GDM group(n=4758,non-GDM pregnant women)according to whether or not they were diagnosed with GDM at 24 to 27+6 gestational weeks by retrospective analysis.Early pregnancy-related influencing factors on the development of GDM in pregnant women were analyzed using multivariate unconditional logistic regression analysis.Based on the biochemical indexes related to glycolipids in early pregnancy and demographic information in pregnant women(8 variables),four machine learning algorithms,namely,decision tree(DT),logistic regression(LR),random forest(RF),and extreme gradient boosting(XGB)were used to build GDM prediction models,and ten-fold cross-validation was used to assess the performance of each model,and area under curve(AUC)of the receiver operating characteristic(ROC)curve among the GDM prediction models constructed by the four algorithms were compared.The study was approved by the Ethics Committee of Fujian Maternity and Child Health Hospital(Approval No.2021KRD018).All pregnant women had signed the informed consent forms for clinical research.Results①The results of multivariate unconditional logistic regression analysis showed that pregnant women with advanced age(delivery age≥35 years)(OR=1.95,95%CI:1.70-2.24,P<0.001),with pre-pregnancy body mass index(BMI)≥18.5-24.0 kg/m^(2)(OR=1.32,95%CI:1.11-1.58,P=0.002),pre-pregnancy BMI≥24.0-28.0 kg/m^(2)(OR=2.17,95%CI:1.73-2.

关 键 词：妊娠初期 糖尿病 妊娠 血糖 血脂 机器学习 算法 Logistic模型 决策树 随机森林 

分 类 号：R714.256[医药卫生—妇产科学]