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.
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.
Abstract:
Very Preterm birth (vPTB) and extreme Preterm birth (xPTB) are the major concerns in maternal and child healthcare and are associated with increased morbidity and mortality. Machine learning methods have traditionally been used to predict preterm births (vPTB and xPTB). However, most medical datasets, including preterm births, are imbalanced in class distribution. Although data-balancing techniques can be employed, complications due to the limited sample size of the minority class are frequently encountered, leading to inconsistent results. This study adopted a novel approach by employing one-class classification (OCC) in conjunction with several strategies to predict instances of vPTB and xPTB within an Emirati pregnant population. We used a well-curated dataset acquired during the first trimester of pregnancy. We employed multiple OCC algorithms and their ensembles involving multiple aggregation strategies to predict vPTB and xPTB in both parous and nulliparous populations. Our approach effectively incorporated only majority class information during training. Our detailed experimental setup demonstrated that the proposed methodology achieved promising performance with a maximum AUC-ROC of 0.823 for the parous population without any explicit modeling of the minority class. Our approach demonstrated robustness and efficacy in identifying at-risk pregnancies within the Emirati population. Our results suggest that one-class classification framework which requires only normal data points for training can be used for early prediction of very preterm and extreme preterm births with reasonable accuracy. In this paper, we applied one-class classification framework only on the Emirati population. Generalizing the proposed approach in this domain requires experimentation on similar datasets from other countries.
