An explainable machine learning model in predicting vaginal birth after cesarean section

Objective Vaginal birth after cesarean section (VBAC) is recommended by obstetrical guidelines or expert consensuses. However, no valid tools can exactly predict who can have a vaginal birth among eligible candidates with one prior cesarean section. In recent years, machine learning (ML) is graduall...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming Yang, Dajian Long, Yunxiu Li, Xiaozhu Liu, Zhi Bai, Zhongjun Li
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:The Journal of Maternal-Fetal & Neonatal Medicine
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/14767058.2025.2546544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849222909236609024
author Ming Yang
Dajian Long
Yunxiu Li
Xiaozhu Liu
Zhi Bai
Zhongjun Li
author_facet Ming Yang
Dajian Long
Yunxiu Li
Xiaozhu Liu
Zhi Bai
Zhongjun Li
author_sort Ming Yang
collection DOAJ
description Objective Vaginal birth after cesarean section (VBAC) is recommended by obstetrical guidelines or expert consensuses. However, no valid tools can exactly predict who can have a vaginal birth among eligible candidates with one prior cesarean section. In recent years, machine learning (ML) is gradually used to develop predictive models in obstetrics and midwifery owing to its excellent performance. This study aimed to develop an explainable ML model to predict the chance of successful VBAC.Methods A total of 2438 pregnant women with trial of labor after cesarean (TOLAC) were analyzed from two tertiary hospitals in Guangdong province of China in the final cohort. The data were collected to establish seven predicting models. Training and internal validation data were collected from the First Dongguan Affiliated Hospital of Guangdong Medical University from January 2012 to December 2022. External validation data were collected from Shenzhen Longhua District Central Hospital from January 2011 to December 2017. Seven predicting models based on ML were developed and evaluated by area under the receiver operating characteristic (AUC) curve. The optimal one was picked out from seven models according to its AUC and other indices. The outcome of the predictive model was interpreted by Shapley Additive exPlanations (SHAP).Results The categorical boosting (CatBoost) model was selected as the predictive model with the greatest AUC for 0.767 (95% CI: 0.685–0.865), the accuracy for 0.652 (95% CI: 0.602–0.713), sensitivity 0.714 (95% CI: 0.576–0.840), and specificity 0.639 (95% CI: 0.574–0.70). Cervical Bishop score and interpregnancy interval showed the greatest impact on successful vaginal birth, according to SHAP results.Conclusions Models based on ML algorithms can be used to predict VBAC. The CatBoost model showed best performance in this study. Based on current evidence-based medical data, clinicians should provide systematic benefit-risk analysis and individualized assessment of VBAC to eligible pregnant women.
format Article
id doaj-art-539e4b36e1f64affa01affd72bb32fe6
institution Kabale University
issn 1476-7058
1476-4954
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series The Journal of Maternal-Fetal & Neonatal Medicine
spelling doaj-art-539e4b36e1f64affa01affd72bb32fe62025-08-26T02:04:59ZengTaylor & Francis GroupThe Journal of Maternal-Fetal & Neonatal Medicine1476-70581476-49542025-12-0138110.1080/14767058.2025.2546544An explainable machine learning model in predicting vaginal birth after cesarean sectionMing Yang0Dajian Long1Yunxiu Li2Xiaozhu Liu3Zhi Bai4Zhongjun Li5Department of Obstetrics, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, ChinaDepartment of Obstetrics, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, ChinaDepartment of Obstetrics, Shenzhen Longhua District Central Hospital, Shenzhen, ChinaDepartment of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, ChinaDepartment of Obstetrics, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, ChinaThe First Clinical Medical School, Guangdong Medical University, Zhanjiang, ChinaObjective Vaginal birth after cesarean section (VBAC) is recommended by obstetrical guidelines or expert consensuses. However, no valid tools can exactly predict who can have a vaginal birth among eligible candidates with one prior cesarean section. In recent years, machine learning (ML) is gradually used to develop predictive models in obstetrics and midwifery owing to its excellent performance. This study aimed to develop an explainable ML model to predict the chance of successful VBAC.Methods A total of 2438 pregnant women with trial of labor after cesarean (TOLAC) were analyzed from two tertiary hospitals in Guangdong province of China in the final cohort. The data were collected to establish seven predicting models. Training and internal validation data were collected from the First Dongguan Affiliated Hospital of Guangdong Medical University from January 2012 to December 2022. External validation data were collected from Shenzhen Longhua District Central Hospital from January 2011 to December 2017. Seven predicting models based on ML were developed and evaluated by area under the receiver operating characteristic (AUC) curve. The optimal one was picked out from seven models according to its AUC and other indices. The outcome of the predictive model was interpreted by Shapley Additive exPlanations (SHAP).Results The categorical boosting (CatBoost) model was selected as the predictive model with the greatest AUC for 0.767 (95% CI: 0.685–0.865), the accuracy for 0.652 (95% CI: 0.602–0.713), sensitivity 0.714 (95% CI: 0.576–0.840), and specificity 0.639 (95% CI: 0.574–0.70). Cervical Bishop score and interpregnancy interval showed the greatest impact on successful vaginal birth, according to SHAP results.Conclusions Models based on ML algorithms can be used to predict VBAC. The CatBoost model showed best performance in this study. Based on current evidence-based medical data, clinicians should provide systematic benefit-risk analysis and individualized assessment of VBAC to eligible pregnant women.https://www.tandfonline.com/doi/10.1080/14767058.2025.2546544Predictive modelsmachine learningvaginal birth after cesarean sectionSHARPCatBoost
spellingShingle Ming Yang
Dajian Long
Yunxiu Li
Xiaozhu Liu
Zhi Bai
Zhongjun Li
An explainable machine learning model in predicting vaginal birth after cesarean section
The Journal of Maternal-Fetal & Neonatal Medicine
Predictive models
machine learning
vaginal birth after cesarean section
SHARP
CatBoost
title An explainable machine learning model in predicting vaginal birth after cesarean section
title_full An explainable machine learning model in predicting vaginal birth after cesarean section
title_fullStr An explainable machine learning model in predicting vaginal birth after cesarean section
title_full_unstemmed An explainable machine learning model in predicting vaginal birth after cesarean section
title_short An explainable machine learning model in predicting vaginal birth after cesarean section
title_sort explainable machine learning model in predicting vaginal birth after cesarean section
topic Predictive models
machine learning
vaginal birth after cesarean section
SHARP
CatBoost
url https://www.tandfonline.com/doi/10.1080/14767058.2025.2546544
work_keys_str_mv AT mingyang anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT dajianlong anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT yunxiuli anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT xiaozhuliu anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT zhibai anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT zhongjunli anexplainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT mingyang explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT dajianlong explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT yunxiuli explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT xiaozhuliu explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT zhibai explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection
AT zhongjunli explainablemachinelearningmodelinpredictingvaginalbirthaftercesareansection