Early prediction of very and extreme preterm births using a one-class classification framework on electronic health

Amir Ahmad1,2, Wasif Khan3, Md Mozakkir Ansari4

  • 1Department of Information Systems and Security, College of Information Technology, United Arab Emirates University, P.O. Box 15551, Al Ain, United Arab Emirates. amirahmad@uaeu.ac.ae.

Scientific Reports
|December 20, 2025
PubMed

Insights

This study introduces a novel one-class classification method for predicting very preterm birth (vPTB) and extreme preterm birth (xPTB) in Emirati women. The approach effectively identifies high-risk pregnancies using only typical data, achieving an AUC-ROC of 0.823.

Area of Science:

  • Maternal-fetal medicine
  • Machine learning in healthcare
  • Computational statistics

Background:

  • Very preterm birth (vPTB) and extreme preterm birth (xPTB) are critical concerns in maternal and child health, linked to significant morbidity and mortality.
  • Traditional machine learning for preterm birth prediction faces challenges due to imbalanced datasets and limited minority class samples.
  • Existing data-balancing techniques often yield inconsistent results when dealing with small minority classes.

Purpose of the Study:

  • To develop and evaluate a novel one-class classification (OCC) approach for predicting vPTB and xPTB in an Emirati pregnant population.
  • To assess the efficacy of OCC algorithms and ensembles using only majority class data for early risk identification.
  • To investigate the performance in both parous and nulliparous subgroups within the study population.

Main Methods:

  • Utilized a curated dataset from the first trimester of pregnancy for an Emirati population.
  • Employed multiple one-class classification algorithms and ensemble methods with various aggregation strategies.
  • Trained models exclusively on majority class data (normal pregnancies), avoiding explicit modeling of the minority class (vPTB/xPTB).

Main Results:

  • Achieved a maximum AUC-ROC of 0.823 for the parous population, demonstrating promising predictive performance.
  • The OCC approach showed robustness and efficacy in identifying pregnancies at risk for vPTB and xPTB.
  • The method successfully predicted at-risk pregnancies without requiring explicit data on preterm birth cases during training.

Conclusions:

  • One-class classification offers a viable framework for the early prediction of vPTB and xPTB with reasonable accuracy.
  • The proposed OCC method, trained solely on normal cases, can effectively identify high-risk pregnancies.
  • Further research is needed to generalize this approach by testing it on datasets from diverse international populations.

Related Concept Videos