Postpartum depression risk prediction using explainable machine learning algorithms
ObjectivePostpartum depression (PPD) is a common and serious mental health complication after childbirth, with potential negative consequences for both the mother and her infant. This study aimed to develop an explainable machine learning model to predict the risk of PPD and to identify its key pred...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1565374/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849240677093736448 |
|---|---|
| author | Xudong Huang Lifeng Zhang Chenyang Zhang Jing Li Chenyang Li |
| author_facet | Xudong Huang Lifeng Zhang Chenyang Zhang Jing Li Chenyang Li |
| author_sort | Xudong Huang |
| collection | DOAJ |
| description | ObjectivePostpartum depression (PPD) is a common and serious mental health complication after childbirth, with potential negative consequences for both the mother and her infant. This study aimed to develop an explainable machine learning model to predict the risk of PPD and to identify its key predictive factors.MethodsA retrospective analysis was conducted on 1,065 women who attended their 6-week postpartum follow-up visit at a tertiary maternal and child healthcare hospital in Shenyang, China, from January to December 2021. Feature selection was performed using LASSO regression and the Boruta algorithm. Eight machine learning algorithms were then employed to construct the prediction models. Model performance was evaluated according to the area under the receiver operator characteristic curve (AUC), sensitivity, specificity, recall, F1 score, and accuracy. Shapley additive explanations (SHAP) were used to visualize the features of the model and individual case predictions.ResultsAmong the 1,065 women, 251 (23.5%) developed PPD. An 11-variable prediction model was developed, with XGBoost showing the best performance on both training and validation sets. After optimizing the model parameters and applying 10-fold cross-validation, the model achieved an average accuracy of 0.95, an average AUC of 0.955, average precision of 0.945, and average specificity of 0.985, indicating excellent predictive performance. The key predictive factors included weight gain during pregnancy, relationship with the mother-in-law, sleep quality, marital relationship, planned pregnancy, fetal sex preference, pregnancy-related anxiety, pelvic-floor muscle endurance, cervix status, attendance at prenatal education classes, and postpartum care satisfaction.ConclusionThe XGBoost model demonstrated optimal performance at predicting PPD and can aid healthcare professionals to identify high-risk individuals. The SHAP method enhanced the model’s interpretability, facilitating a better understanding of the causes of PPD, how to prevent it, and how to improve patient outcomes. |
| format | Article |
| id | doaj-art-fa63b702c582453e8f1a35a20e879d0c |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-fa63b702c582453e8f1a35a20e879d0c2025-08-20T04:00:28ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-08-011210.3389/fmed.2025.15653741565374Postpartum depression risk prediction using explainable machine learning algorithmsXudong Huang0Lifeng Zhang1Chenyang Zhang2Jing Li3Chenyang Li4Department of Science and Education, Shenyang Maternity and Child Health Hospital, Shenyang, ChinaDepartment of Maternal, Child and Adolescent Health, School of Public Health, Shenyang Medical College, Shenyang, ChinaDepartment of Science and Education, Shenyang Maternity and Child Health Hospital, Shenyang, ChinaDepartment of Science and Education, Shenyang Maternity and Child Health Hospital, Shenyang, ChinaDepartment of Science and Education, Shenyang Maternity and Child Health Hospital, Shenyang, ChinaObjectivePostpartum depression (PPD) is a common and serious mental health complication after childbirth, with potential negative consequences for both the mother and her infant. This study aimed to develop an explainable machine learning model to predict the risk of PPD and to identify its key predictive factors.MethodsA retrospective analysis was conducted on 1,065 women who attended their 6-week postpartum follow-up visit at a tertiary maternal and child healthcare hospital in Shenyang, China, from January to December 2021. Feature selection was performed using LASSO regression and the Boruta algorithm. Eight machine learning algorithms were then employed to construct the prediction models. Model performance was evaluated according to the area under the receiver operator characteristic curve (AUC), sensitivity, specificity, recall, F1 score, and accuracy. Shapley additive explanations (SHAP) were used to visualize the features of the model and individual case predictions.ResultsAmong the 1,065 women, 251 (23.5%) developed PPD. An 11-variable prediction model was developed, with XGBoost showing the best performance on both training and validation sets. After optimizing the model parameters and applying 10-fold cross-validation, the model achieved an average accuracy of 0.95, an average AUC of 0.955, average precision of 0.945, and average specificity of 0.985, indicating excellent predictive performance. The key predictive factors included weight gain during pregnancy, relationship with the mother-in-law, sleep quality, marital relationship, planned pregnancy, fetal sex preference, pregnancy-related anxiety, pelvic-floor muscle endurance, cervix status, attendance at prenatal education classes, and postpartum care satisfaction.ConclusionThe XGBoost model demonstrated optimal performance at predicting PPD and can aid healthcare professionals to identify high-risk individuals. The SHAP method enhanced the model’s interpretability, facilitating a better understanding of the causes of PPD, how to prevent it, and how to improve patient outcomes.https://www.frontiersin.org/articles/10.3389/fmed.2025.1565374/fullpostpartum depressionmachine learningpredictive modelinfluencing factorsmaternal health |
| spellingShingle | Xudong Huang Lifeng Zhang Chenyang Zhang Jing Li Chenyang Li Postpartum depression risk prediction using explainable machine learning algorithms Frontiers in Medicine postpartum depression machine learning predictive model influencing factors maternal health |
| title | Postpartum depression risk prediction using explainable machine learning algorithms |
| title_full | Postpartum depression risk prediction using explainable machine learning algorithms |
| title_fullStr | Postpartum depression risk prediction using explainable machine learning algorithms |
| title_full_unstemmed | Postpartum depression risk prediction using explainable machine learning algorithms |
| title_short | Postpartum depression risk prediction using explainable machine learning algorithms |
| title_sort | postpartum depression risk prediction using explainable machine learning algorithms |
| topic | postpartum depression machine learning predictive model influencing factors maternal health |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1565374/full |
| work_keys_str_mv | AT xudonghuang postpartumdepressionriskpredictionusingexplainablemachinelearningalgorithms AT lifengzhang postpartumdepressionriskpredictionusingexplainablemachinelearningalgorithms AT chenyangzhang postpartumdepressionriskpredictionusingexplainablemachinelearningalgorithms AT jingli postpartumdepressionriskpredictionusingexplainablemachinelearningalgorithms AT chenyangli postpartumdepressionriskpredictionusingexplainablemachinelearningalgorithms |