基于列线图模型的产后抑郁风险预测  

Risk prediction of postpartum depression based on a nomogram model

作　　者：金兰 田文琴 拓明花 尚玉秀[1] JIN Lan;TIAN Wen-qin;TA Ming-hua;SHANG Yu-xiu(Key Laboratory of Environmental Factors and Chronic Disease Control in Ningxia,School of Public Health,Ningxia Medical University,Yinchuan,Ningxia 750000,China;不详)

机构地区：[1]宁夏医科大学公共卫生学院宁夏环境因素与慢性病控制重点实验室,宁夏银川750000 [2]中卫市人民医院妇产科 [3]中卫市妇幼保健院妇产科

出　　处：《中国妇幼保健》2025年第7期1185-1188,共4页Maternal and Child Health Care of China

基　　金：宁夏回族自治区自然科学基金资助项目(2023AAC03223)。

摘　　要：目的 探讨产妇产后抑郁的危险因素,建立并评估个性化预测产后抑郁的列线图模型及在线动态列线图。方法 选取2021年5月—2022年3月在中卫市人民医院、中卫市妇幼保健院、中卫市中医院产科住院待产的329例孕妇为研究对象,采用爱丁堡产后抑郁量表(EPDS)评估产后抑郁发生情况,采用多因素logistic回归模型分析产后抑郁的影响因素,通过R软件绘制列线图模型,应用Shiny Apps绘制在线动态列线图,通过受试者工作特征(ROC)曲线、校准曲线、Hosmer-Lemeshow拟合优度检验、临床决策曲线验证模型的预测效能。结果 多因素logistic回归分析结果显示:夫妻关系(OR=2.784,95%CI:1.272~6.095)、产前焦虑(OR=2.417,95%CI:1.193~4.897)及产前抑郁(OR=4.245,95%CI:2.320~7.767)均为产后抑郁的独立危险因素(均P<0.05)。以上述因素构建列线图模型,绘制ROC曲线,得到曲线下面积(AUC)为0.743,95%CI为0.683~0.803。绘制校准曲线,校准曲线斜率接近1,χ^(2)=0.298,P>0.05,提示校准度高。临床决策曲线表明该列线图预测模型具有良好的临床实用性。结论 构建的在线动态列线图具有良好的预测效能,可为临床早期筛查、识别高危人群及降低孕产妇产后抑郁的发生提供参考依据。Objective To explore the risk factors of postpartum depression,develop and evaluate a personalized predictive nomogram model and an online dynamic nomogram of postpartum depression.Methods A total of 329 pregnant women hospitalized for delivery in Zhongwei Municipal People's Hospital,Zhongwei Maternal and Child Health Care Hospital,and Zhongwei Hospital of Traditional Chinese Medicine from May 2021 to March 2022 were selected as the study subjects,and Edinburgh postnatal depression scale(EPDS)was used to investigate postpartum depression,logistic regression model was used to analyze the influencing factors of postpartum depression.R sofware was used to draw nomogram model,Shiny Apps was used to draw online dynamic nomogram,the predictive efficacy of the model was validated by receiver operating characteristic(ROC)curve,calibration curve,Hosmer-Lemeshow goodness-of-fit test,and clinical decision curve.Results Multivariate logistic regression analysis showed that spousal relationship(0R=2.784,95%Cl:1.272-6.095),prenatal anxiety(OR=2.417,95%Cl:1.193-4.897),and prenatal depression(OR=4.245,95%CI:2.320-7.767)were independent risk factors for the occurrence of postpartum depression.Based on the above factors,nomogram model was constructed,ROC curve was drawn,the area under the curve(AUC)was 0.743(95%CI:0.683-0.803),calibration curve was drawn,the slope closed to 1(χ^(2)=0.298,P>O.05),the calibration degree was high.Clinical decision curve showed that the model had a good clinical practicability.Conclusion The online dynamic nomogram constructed in this study has good predictive efficiency,which can provide a reference for early clinical screening,identification of high-risk groups,and reduction of the incidence rate of postpartum depression.

关 键 词：产后抑郁 危险因素 列线图模型 风险预测 

分 类 号：R714.6[医药卫生—妇产科学]