中国妇幼健康研究2025，Vol.36Issue(3)：13-20,8.DOI:10.3969/j.issn.1673-5293.2025.03.003
产后抑郁风险预测模型的构建与验证
Construction and validation of a risk prediction model for postpartum depression
摘要
Abstract
Objective To explore the construction and validation of a risk prediction model applied to the early primary screening of women for postpartum depression in the early postnatal period.Methods A total of 438 women who delivered as inpatients in The Affiliated Hospital of North Sichuan Medical College from 1 October 2022 to 1 October 2023 were selected as the study subjects.Depressive symptoms were assessed using the Edinburgh postnatal depression scale(EPDS)within 1 week postpartum,with a threshold score of 9.5 used to divide the study subjects into the postpartum depression group(n=114)and the non-postpartum depression group(n=324).Multivariate Logistic regression was used to identify the risk factors for postpartum depressive symptoms,and a visual nomogram model was further constructed.The model's discrimination and calibration were evaluated using the receiver operating characteristic(ROC)curves and the Hosmer-Lemeshow(H-L)goodness-of-fit test.The model was internally validated using the Bootstrap method,and its clinical applicability was assessed using decision curve analysis(DCA).Results Multivariate logistic regression analysis showed that age≥30 years,higher prenatal BMI,and higher education level were independent protective factors against postpartum depression(OR ranged from 0.239 to 0.903,P＜0.05);a family history of depression,depressive symptoms in late pregnancy,and experiencing persistent low mood for at least two weeks in the year prior to pregnancy were independent risk factors for postpartum depression(OR ranged from 4.981 to 13.215,P＜0.05).The area under the ROC curve(AUC)of the model was 0.831(95％CI:0.785～0.877),with a sensitivity of 75.4％and specificity of 77.5％;the H-L goodness-of-fit test showed x2=2.773,P＞0.05;and the decision curve analysis(DCA)demonstrated clinical applicability within the threshold probability range of 10％to 100％,with the maximum net benefit.Conclusion The prediction model of postpartum depression constructed in this study has good predictive value and clinical applicability,which provides a scientific basis for early and efficient screening of postpartum depressive symptoms.关键词
孕产妇/产后抑郁/预测模型/列线图Key words
pregnant and postpartum women/postpartum depression/prediction model/nomogram分类
医药卫生引用本文复制引用
谭欣林,黄玥,漆洪波,石琪..产后抑郁风险预测模型的构建与验证[J].中国妇幼健康研究,2025,36(3):13-20,8.基金项目
国家工业和信息化部、国家卫生健康委员会《5G+医疗健康应用试点项目》批准立项项目(JKZX2022-5G03) （JKZX2022-5G03）
