基于Logistic回归分析的正常糖耐量孕妇所娩新生儿低血糖危险度预测模型的构建与验证  

Construction and validation of a predictive model for risk of hypoglycemia in neonates delivered by pregnant women with normal glucose tolerance based on Logistic regression analysis

作　　者：徐超英 房玥 吴婷婷 陈黎慧 杨倩 王月红 XU Chaoying;FANG Yue;WU Tingting;CHEN Lihui;YANG Qian;WANG Yuehong(Department of Obstetrics,Suzhou City Ninth People′s Hospital of Jiangsu Province,Suzhou,Jiangsu,215200;Departrment of Neonatology,Suzhou City Ninth People′s Hospital of Jiangsu Province,Suzhou,Jiangsu,215200)

机构地区：[1]江苏省苏州市第九人民医院产科,江苏苏州215200 [2]江苏省苏州市第九人民医院新生儿科,江苏苏州215200

出　　处：《实用临床医药杂志》2022年第17期111-115,共5页Journal of Clinical Medicine in Practice

基　　金：江苏省苏州市第九人民医院科研立项项目(YK202044)。

摘　　要：目的 构建并验证正常糖耐量孕妇所娩新生儿低血糖危险度的预测模型。方法 回顾性分析1 865例正常糖耐量孕妇及其新生儿的临床资料,通过随机数字法按7∶3的比例将其分为建模人群1 305例和验证人群560例。在建模人群中,以新生儿是否发生低血糖分为低血糖组91例和正常组1 214例,比较2组临床指标水平。将有统计学意义的指标纳入多因素Logistic回归分析,筛选新生儿低血糖的危险因素,并基于筛选结果建立预测模型。采用拟合优度检验和受试者工作特征(ROC)曲线评价模型表现,将验证人群资料纳入预测模型中验证模型的预测效能。结果 建模人群与验证人群的临床指标水平比较,差异无统计学意义(P>0.05)。低血糖组与正常组在产妇孕期体质量增长、预估胎儿体质量、分娩孕周、接受产前培训次数、分娩方式及产后喂养方面比较,差异有统计学意义(P<0.01)。多因素Logistic回归分析显示,孕期体质量增长多(OR=2.939,95%CI:1.941~6.462)、预估胎儿体质量较轻(OR=1.590,95%CI:1.158~2.906)、分娩孕周早(OR=1.815,95%CI:1.397~3.872)、产前培训次数少(OR=1.828,95%CI:1.281~3.045)、分娩方式为剖宫产(OR=3.411,95%CI:2.196~5.949)、产后喂养不当(OR=1.529,95%CI:1.182~2.748)是正常糖耐量孕妇所娩新生儿低血糖的危险因素(P<0.05)。根据危险因素建立预测模型,拟合优度偏差性检验无统计学意义(χ~2=1.619,P=0.983),ROC曲线的曲线下面积为0.890(95%CI:0.842~0.937),表明模型无过拟合现象且区分能力较强。将验证人群的资料纳入预测模型中进行验证发现,ROC曲线的曲线下面积为0.864(95%CI:0.808~0.920),灵敏度为86.10%,特异度为82.50%。结论 基于孕期体质量增长、预估胎儿体质量、分娩孕周、产前培训次数、分娩方式及产后喂养构建的正常糖耐量孕妇所娩新生儿低血糖危险度预测模型,具有一定的应用价值。Objective To construct and validate a predictive model for risk of hypoglycemia in neonates delivered by pregnant women with normal glucose tolerance.Methods The clinical materials of 1 865 pregnant women with normal glucose tolerance and their newborns were retrospectively analyzed,and they were divided into modeling population with 1 305 cases and validation population with 560 cases according to a ratio of 7 to 3 by random number method.In the modeling population,they were divided into hypoglycemia group 91 cases and normal group 1 214 cases according to occurrence of neonatal hypoglycemia,and the clinical indexes were compared between the two groups.The indicators with statistical significance were included in the multivariate Logistic regression analysis to screen the risk factors of neonatal hypoglycemia,and a prediction model was established based on the screening results.The performance of the model was evaluated by chi-square goodness-of-fit test and receiver operating characteristic( ROC) curve,and the validation population data was included in the predictionmodel to verify the prediction efficiency of the model.Results There were no significant differences in the clinical materials between the modeling population and the validation population( P > 0.05).There were significant differences in the growth of body mass during pregnancy,estimated fetal body mass,gestational weeks of delivery,number of prenatal training,delivery mode and postpartum feeding between the hypoglycemic group and the normal group( P < 0.01).Multivariate Logistic regression analysis showed that increased growth of body mass during pregnancy( OR =2.939;95% CI,1.941 to 6.462),lighter estimated fetal body mass( OR = 1.590;95% CI,1.158to 2.906),earlier gestational week( OR = 1.815;95% CI,1.397 to 3.872),less number of prenatal training( OR = 1.828;95% CI,1.281 to 3.045),cesarean section( OR = 3.411;95% CI,2.196 to 5.949) and improper postpartum feeding( OR = 1.529;95% CI,1.182 to 2.748) were the risk factors of neonatal hypoglycemia in

关 键 词：糖耐量 新生儿 低血糖 危险度 预测模型 体质量 分娩方式 孕妇 

分 类 号：R722.1[医药卫生—儿科] R587.1[医药卫生—临床医学]