Developing a predictive model for stillbirth risk using machine learning algorithms

Mayasee Kuanakewinyoo, Arthit I ntarasit, Jarunee Saelee, Jirapond Muangprathub

Abstract

Stillbirths continue to be a significant global issue, reflecting the quality of obstetric care. In Thailand, stillbirth remains a concern, especially in southern provinces like Pattani. Traditional risk identification focuses on historical obstetric complications, but there is a need for advanced technology to improve early detection and prevention. This study investigates the factors influencing stillbirth risk by analyzing perinatal data from 2018 to 2021 in Pattani Province. A machine learning-based predictive model was developed using various algorithms, including Naïve Bayes, logistic regression, deep learning, decision tree, random forest, and gradient-boosted trees, to handle imbalanced datasets. Performance comparisons of these models were conducted, and the best-performing model was implemented into a web application to provide personalized recommendations to pregnant women. The study highlights the importance of advanced data analytics in stillbirth prevention and offers an innovative, accessible solution for pregnant women to manage and monitor their pregnancies. The system not only improves the prediction of stillbirth risks but also provides an interactive, low-cost platform for delivering real-time suggestions, aiming to reduce stillbirth occurrences and improve maternal health outcomes.

Authors

Mayasee Kuanakewinyoo
Arthit I ntarasit
Jarunee Saelee
Jirapond Muangprathub
jirapond.m@psu.ac.th (Primary Contact)
Kuanakewinyoo, M. ., ntarasit, A. I., Saelee, J. ., & Muangprathub, J. . (2025). Developing a predictive model for stillbirth risk using machine learning algorithms. International Journal of Innovative Research and Scientific Studies, 8(4), 1897–1907. https://doi.org/10.53894/ijirss.v8i4.8259

Article Details

No Related Submission Found