The Application of Machine Learning Models to Predict Stillbirths

<i>Background and Objectives</i>: This study aims to evaluate the predictive value of comprehensive data obtained in obstetric clinics for the detection of stillbirth and the predictive ability set of machine learning models for stillbirth. <i>Material and Method</i>: The stu...

Full description

Saved in:
Bibliographic Details
Main Authors: Oguzhan Gunenc, Sukran Dogru, Fikriye Karanfil Yaman, Huriye Ezveci, Ulfet Sena Metin, Ali Acar
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Medicina
Subjects:
Online Access:https://www.mdpi.com/1648-9144/61/3/472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279729263804416
author Oguzhan Gunenc
Sukran Dogru
Fikriye Karanfil Yaman
Huriye Ezveci
Ulfet Sena Metin
Ali Acar
author_facet Oguzhan Gunenc
Sukran Dogru
Fikriye Karanfil Yaman
Huriye Ezveci
Ulfet Sena Metin
Ali Acar
author_sort Oguzhan Gunenc
collection DOAJ
description <i>Background and Objectives</i>: This study aims to evaluate the predictive value of comprehensive data obtained in obstetric clinics for the detection of stillbirth and the predictive ability set of machine learning models for stillbirth. <i>Material and Method</i>: The study retrospectively included all stillbirths followed up at a hospital between January 2015 and March 2024 and randomly selected pregnancies that resulted in a live birth. The electronic record system accessed pregnant women’s maternal, fetal, and obstetric characteristics. Based on the perinatal characteristics of the cases, four distinct machine learning classifiers were developed: logistic regression (LR), Support Vector Machine (SVM), Random Forest (RF), and multilayer perceptron (MLP). <i>Results</i>: The study included a total of 951 patients, 499 of whom had live births and 452 of whom had stillbirths. The consanguinity rate, fetal anomalies, history of previous stillbirth, maternal thrombosis, oligohydramnios, and abruption of the placenta were significantly higher in the stillbirth group (<i>p</i> = 0.001). Previous stillbirth histories resulted in a higher rate of stillbirth (OR: 7.31, 95%CI: 2.76–19.31, <i>p</i> = 0.001). Previous thrombosis histories resulted in a higher rate of stillbirth (OR: 14.13, 95%CI: 5.08–39.31, <i>p</i> = 0.001). According to the accuracy estimates of the machine learning models, RF is the most successful model with 96.8% accuracy, 96.3% sensitivity, and 97.2% specificity. <i>Conclusions</i>: The RF machine learning approach employed to predict stillbirths had an accuracy rate of 96.8%. We believe that the elevated success rate of stillbirth prediction using maternal, neonatal, and obstetric risk factors will assist healthcare providers in reducing stillbirth rates through prenatal care interventions.
format Article
id doaj-art-cdf3ff08ede94bfb97dc9eced75fe83a
institution OA Journals
issn 1010-660X
1648-9144
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Medicina
spelling doaj-art-cdf3ff08ede94bfb97dc9eced75fe83a2025-08-20T01:49:00ZengMDPI AGMedicina1010-660X1648-91442025-03-0161347210.3390/medicina61030472The Application of Machine Learning Models to Predict StillbirthsOguzhan Gunenc0Sukran Dogru1Fikriye Karanfil Yaman2Huriye Ezveci3Ulfet Sena Metin4Ali Acar5Konya City Hospital, Konya 42020, TurkeyKonya City Hospital, Konya 42020, TurkeyDivision of Perinatology, Department of Obstetrics and Gynecology, Medical School of Meram, Necmettin Erbakan University, Konya 42090, TurkeyDivision of Perinatology, Department of Obstetrics and Gynecology, Medical School of Meram, Necmettin Erbakan University, Konya 42090, TurkeyDepartment of Obstetrics and Gynecology, Medical School of Meram, Necmettin Erbakan University, Konya 42090, TurkeyDepartment of Obstetrics and Gynecology, Medical School of Meram, Necmettin Erbakan University, Konya 42090, Turkey<i>Background and Objectives</i>: This study aims to evaluate the predictive value of comprehensive data obtained in obstetric clinics for the detection of stillbirth and the predictive ability set of machine learning models for stillbirth. <i>Material and Method</i>: The study retrospectively included all stillbirths followed up at a hospital between January 2015 and March 2024 and randomly selected pregnancies that resulted in a live birth. The electronic record system accessed pregnant women’s maternal, fetal, and obstetric characteristics. Based on the perinatal characteristics of the cases, four distinct machine learning classifiers were developed: logistic regression (LR), Support Vector Machine (SVM), Random Forest (RF), and multilayer perceptron (MLP). <i>Results</i>: The study included a total of 951 patients, 499 of whom had live births and 452 of whom had stillbirths. The consanguinity rate, fetal anomalies, history of previous stillbirth, maternal thrombosis, oligohydramnios, and abruption of the placenta were significantly higher in the stillbirth group (<i>p</i> = 0.001). Previous stillbirth histories resulted in a higher rate of stillbirth (OR: 7.31, 95%CI: 2.76–19.31, <i>p</i> = 0.001). Previous thrombosis histories resulted in a higher rate of stillbirth (OR: 14.13, 95%CI: 5.08–39.31, <i>p</i> = 0.001). According to the accuracy estimates of the machine learning models, RF is the most successful model with 96.8% accuracy, 96.3% sensitivity, and 97.2% specificity. <i>Conclusions</i>: The RF machine learning approach employed to predict stillbirths had an accuracy rate of 96.8%. We believe that the elevated success rate of stillbirth prediction using maternal, neonatal, and obstetric risk factors will assist healthcare providers in reducing stillbirth rates through prenatal care interventions.https://www.mdpi.com/1648-9144/61/3/472stillbirthmachine learningpredictionodds ratio
spellingShingle Oguzhan Gunenc
Sukran Dogru
Fikriye Karanfil Yaman
Huriye Ezveci
Ulfet Sena Metin
Ali Acar
The Application of Machine Learning Models to Predict Stillbirths
Medicina
stillbirth
machine learning
prediction
odds ratio
title The Application of Machine Learning Models to Predict Stillbirths
title_full The Application of Machine Learning Models to Predict Stillbirths
title_fullStr The Application of Machine Learning Models to Predict Stillbirths
title_full_unstemmed The Application of Machine Learning Models to Predict Stillbirths
title_short The Application of Machine Learning Models to Predict Stillbirths
title_sort application of machine learning models to predict stillbirths
topic stillbirth
machine learning
prediction
odds ratio
url https://www.mdpi.com/1648-9144/61/3/472
work_keys_str_mv AT oguzhangunenc theapplicationofmachinelearningmodelstopredictstillbirths
AT sukrandogru theapplicationofmachinelearningmodelstopredictstillbirths
AT fikriyekaranfilyaman theapplicationofmachinelearningmodelstopredictstillbirths
AT huriyeezveci theapplicationofmachinelearningmodelstopredictstillbirths
AT ulfetsenametin theapplicationofmachinelearningmodelstopredictstillbirths
AT aliacar theapplicationofmachinelearningmodelstopredictstillbirths
AT oguzhangunenc applicationofmachinelearningmodelstopredictstillbirths
AT sukrandogru applicationofmachinelearningmodelstopredictstillbirths
AT fikriyekaranfilyaman applicationofmachinelearningmodelstopredictstillbirths
AT huriyeezveci applicationofmachinelearningmodelstopredictstillbirths
AT ulfetsenametin applicationofmachinelearningmodelstopredictstillbirths
AT aliacar applicationofmachinelearningmodelstopredictstillbirths