Quick Search
A pilot study on the role of artificial intelligence in predicting preterm labor
Ece Akca Salık1, Zafer Bütün2, Yeliz Kaya3, Özer Çelik4, Tuğba Tahta5, Arzu Altun Yavuz61Department of Gynecology and Obstetrics, Eskisehir City Hospital, Eskisehir, Turkey2Department of Perinatology, Private Clinic, Eskisehir, Turkey
3Department of Gynecology and Obstetrics, Eskisehir Osmangazi University Faculty of Health Sciences, Eskisehir, Turkey
4Vocational School of Information Technologies, Anadolu University, Eskisehir, Turkey
5Department of Midwifery, Faculty of Health Sciences, Ankara Medipol University, Ankara, Turkey
6Department of Statistics, Eskisehir Osmangazi University, Faculty of Science, Eskisehir, Turkey
INTRODUCTION: Preterm labor is a major obstetric challenge that contributes significantly to neonatal morbidity and mortality. This pilot study investigated the feasibility of machine learning techniques for predicting the risk of threatened preterm labor, rather than confirmed preterm birth, among first-time mothers using readily available sociodemographic and obstetric variables.
METHODS: This retrospective, single-center study included 102 nulliparous women with singleton pregnancies. Five machine learning models were developed using basic clinical parameters. Model performance was evaluated using an 80/20 training–test split and assessed based on accuracy, ROC-AUC, sensitivity, and specificity.
RESULTS: The XGBoost classifier demonstrated the best performance, with an accuracy of 70% and a ROC-AUC of 0.64. Body mass index and a history of abortus imminens were the most influential predictors.
DISCUSSION AND CONCLUSION: Machine learning models based on simple clinical data can modestly predict threatened preterm labor. Although these models are not intended for immediate clinical application, the findings demonstrate feasibility and support further large-scale, externally validated studies incorporating maternal and neonatal outcomes.
Keywords: Artificial intelligence, machine learning, nulliparous women, predictive modeling, preterm labor.
Manuscript Language: English
