基于母乳生物标志物的产妇泌乳启动延迟预警模型构建与验证

Construction of warning model of maternal lactation initiation delay based on breast milk biomarkers and its verification

目的构建基于母乳生物标志物的产妇泌乳启动延迟预警模型并评估其效能。方法选取486例产妇作为研究对象,按7∶3比例分为建模组340例和验证组146例,并将建模组产妇根据是否泌乳启动成功分为泌乳启动成功组255例和泌乳启动延迟组85例。采用Logistic回归分析明确产妇泌乳Ⅱ期启动延迟的影响因素。采用R软件构建预测产妇泌乳Ⅱ期启动延迟风险的列线图模型,通过受试者工作特征(ROC)曲线和校准曲线评估列线图模型的区分度和一致性。结果泌乳启动延迟组年龄31~40岁者占比、初产妇占比、剖宫产者占比和母乳中钠离子、蛋白质水平均高于泌乳启动成功组,母乳中乳糖、柠檬酸盐水平低于泌乳启动成功组,差异有统计学意义(P<0.05)。多因素Logistic回归分析显示,母乳中钠离子、乳糖、柠檬酸盐水平是产妇泌乳Ⅱ期启动延迟的影响因素(P<0.05)。ROC曲线显示,列线图模型在建模组和验证组中预测泌乳Ⅱ期启动延迟的曲线下面积(AUC)均为0.998;Hosmer-Lemeshow拟合优度检验显示,列线图模型的校准曲线预测值与实际值基本一致(建模组χ^(2)=6.062,P=0.511;验证组χ^(2)=7.288,P=0.506)。结论基于母乳生物标志物乳糖、钠离子、柠檬酸盐构建的预测产妇泌乳Ⅱ期启动延迟风险的列线图模型,一致性和区分度均较好。

Objective To construct an early warning model of delayed initiation of maternal lactation based on breast milk biomarkers and to evaluate its effectiveness.Methods A total of 486 puerperae were selected as study objects,and were divided into modeling group(340 cases)and verification group(146 cases)according to a ratio of 7∶3,the modeling group was further divided into delayed lactation initiation group(85 cases)and successful lactation initiation group(255 cases)according to whether the lactation initiation was successful.Logistic regression was used to analyze risk factors for delayed initiation of maternal stageⅡlactation.R software was applied to construct a nomogram model for predicting the risk of delayed initiation of maternal stageⅡlactation.The receiver operating characteristic(ROC)curve and calibration curve were used to evaluate the differentiation and consistency of the nomogram models.Results The proportions of patients aged 31 to 40 years old,primipara,cesarean section,and the sodium ion concentration and protein level in the delayed lactation initiation group were greatly higher than those in successful lactation initiation group,the lactose and citrate levels were lower than those in the successful lactation initiation group(P<0.05).The multivariate Logistic analysis showed that sodium ion,lactose and citrate levels were the influencing factors of delayed initiation of stageⅡlactation(P<0.05).ROC curve showed that the area under the curve(AUC)of the nomogram model for predicting lactation stageⅡinitiation delay was 0.998 in both the modeling group and the validation group.Hosmer-Lemeshow goodness of fit test showed that the predicted value of calibration curve of the nomogram model was basically consistent with the actual value(modeling group:χ^(2)=6.062,P=0.511;verification group:χ^(2)=7.288,P=0.506).Conclusion The nomogram model based on lactose,sodium ion and citrate of breast milk biomarkers to predict the risk of delayed initiation of puerpera lactation stageⅡhas good consistency and discrimination.