Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer

Research questionCan machine learning models accurately predict the risk of early miscarriage following single vitrified-warmed blastocyst transfer (SVBT)?DesignA dual-center retrospective analysis of 1,664 SVBT cycles, including 308 early miscarriage cases, was conducted across two reproductive cen...

Full description

Saved in:
Bibliographic Details
Main Authors: Lidan Liu, Bo Liu, Huimei Wu, Qiuying Gan, Qianyi Huang, Mujun Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1557667/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151116990316544
author Lidan Liu
Bo Liu
Huimei Wu
Qiuying Gan
Qianyi Huang
Mujun Li
author_facet Lidan Liu
Bo Liu
Huimei Wu
Qiuying Gan
Qianyi Huang
Mujun Li
author_sort Lidan Liu
collection DOAJ
description Research questionCan machine learning models accurately predict the risk of early miscarriage following single vitrified-warmed blastocyst transfer (SVBT)?DesignA dual-center retrospective analysis of 1,664 SVBT cycles, including 308 early miscarriage cases, was conducted across two reproductive centers. Multiple machine learning models, such as Logistic Regression, Random Forest, Gradient Boosting, and Voting Classifier, were developed. Metrics including Area Under the Curve(AUC), accuracy, precision, recall, F1 score, and specificity were used to evaluate model performance. Key predictors were identified through Mutual Information and Recursive Feature Elimination (RFE).ResultsMaternal age, paternal age, endometrial thickness, blastocyst quality, and ovarian stimulation parameters were identified as critical predictors. Compared to traditional statistical models such as logistic regression (AUC = 0.584), ensemble models demonstrated significantly improved predictive performance. The Voting Classifier achieved the highest AUC (0.836), accuracy (0.780), precision (0.914), and specificity (0.942), outperforming individual machine learning classifiers. The Gradient Boosting Classifier also exhibited strong performance (AUC 0.831, accuracy 0.777), confirming the effectiveness of ensemble learning in capturing complex predictors of early miscarriage risk.ConclusionEnsemble machine learning models, particularly the Voting Classifier and Gradient Boosting Classifier, significantly improve the prediction of early miscarriage following SVBT. These models provide accurate, individualized risk assessments, enhancing clinical decision-making and advancing personalized care in ART.
format Article
id doaj-art-0124bb6c951e491b9a6078f266c1a659
institution OA Journals
issn 1664-2392
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-0124bb6c951e491b9a6078f266c1a6592025-08-20T02:26:22ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-04-011610.3389/fendo.2025.15576671557667Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transferLidan Liu0Bo Liu1Huimei Wu2Qiuying Gan3Qianyi Huang4Mujun Li5Guangxi Reproductive Medical Center, The First Affiliated Hospital of Guangxi Medical University, Nanning, ChinaGuangxi Reproductive Medical Center, The First Affiliated Hospital of Guangxi Medical University, Nanning, ChinaGuangxi Reproductive Medical Center, The First Affiliated Hospital of Guangxi Medical University, Nanning, ChinaReproductive Center, Nanning Maternity and Child Health Hospital, Nanning, Guangxi, ChinaGuangxi Reproductive Medical Center, The First Affiliated Hospital of Guangxi Medical University, Nanning, ChinaGuangxi Reproductive Medical Center, The First Affiliated Hospital of Guangxi Medical University, Nanning, ChinaResearch questionCan machine learning models accurately predict the risk of early miscarriage following single vitrified-warmed blastocyst transfer (SVBT)?DesignA dual-center retrospective analysis of 1,664 SVBT cycles, including 308 early miscarriage cases, was conducted across two reproductive centers. Multiple machine learning models, such as Logistic Regression, Random Forest, Gradient Boosting, and Voting Classifier, were developed. Metrics including Area Under the Curve(AUC), accuracy, precision, recall, F1 score, and specificity were used to evaluate model performance. Key predictors were identified through Mutual Information and Recursive Feature Elimination (RFE).ResultsMaternal age, paternal age, endometrial thickness, blastocyst quality, and ovarian stimulation parameters were identified as critical predictors. Compared to traditional statistical models such as logistic regression (AUC = 0.584), ensemble models demonstrated significantly improved predictive performance. The Voting Classifier achieved the highest AUC (0.836), accuracy (0.780), precision (0.914), and specificity (0.942), outperforming individual machine learning classifiers. The Gradient Boosting Classifier also exhibited strong performance (AUC 0.831, accuracy 0.777), confirming the effectiveness of ensemble learning in capturing complex predictors of early miscarriage risk.ConclusionEnsemble machine learning models, particularly the Voting Classifier and Gradient Boosting Classifier, significantly improve the prediction of early miscarriage following SVBT. These models provide accurate, individualized risk assessments, enhancing clinical decision-making and advancing personalized care in ART.https://www.frontiersin.org/articles/10.3389/fendo.2025.1557667/fullearly miscarriagesingle vitrified-warmed blastocyst transfer (SVBT)machine learning (ML)voting classifiergradient boosting
spellingShingle Lidan Liu
Bo Liu
Huimei Wu
Qiuying Gan
Qianyi Huang
Mujun Li
Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
Frontiers in Endocrinology
early miscarriage
single vitrified-warmed blastocyst transfer (SVBT)
machine learning (ML)
voting classifier
gradient boosting
title Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
title_full Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
title_fullStr Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
title_full_unstemmed Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
title_short Optimizing predictive features using machine learning for early miscarriage risk following single vitrified-warmed blastocyst transfer
title_sort optimizing predictive features using machine learning for early miscarriage risk following single vitrified warmed blastocyst transfer
topic early miscarriage
single vitrified-warmed blastocyst transfer (SVBT)
machine learning (ML)
voting classifier
gradient boosting
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1557667/full
work_keys_str_mv AT lidanliu optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer
AT boliu optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer
AT huimeiwu optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer
AT qiuyinggan optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer
AT qianyihuang optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer
AT mujunli optimizingpredictivefeaturesusingmachinelearningforearlymiscarriageriskfollowingsinglevitrifiedwarmedblastocysttransfer