Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015

Eva Malacova, Sawitchaya Tippaya, Helen D. Bailey, Kevin Chai, Brad M. Farrant, Amanuel T. Gebremedhin, Helen Leonard, Michael L. Marinovich, Natasha Nassar, Aloke Phatak, Camille Raynes-Greenow, Annette K. Regan, Antonia W. Shand, Carrington C.J. Shepherd, Ravisha Srinivasjois, Gizachew A. Tessema, Gavin Pereira

Research output: Contribution to journalArticle

Abstract

Quantification of stillbirth risk has potential to support clinical decision-making. Studies that have attempted to quantify stillbirth risk have been hampered by small event rates, a limited range of predictors that typically exclude obstetric history, lack of validation, and restriction to a single classifier (logistic regression). Consequently, predictive performance remains low, and risk quantification has not been adopted into antenatal practice. The study population consisted of all births to women in Western Australia from 1980 to 2015, excluding terminations. After all exclusions there were 947,025 livebirths and 5,788 stillbirths. Predictive models for stillbirth were developed using multiple machine learning classifiers: regularised logistic regression, decision trees based on classification and regression trees, random forest, extreme gradient boosting (XGBoost), and a multilayer perceptron neural network. We applied 10-fold cross-validation using independent data not used to develop the models. Predictors included maternal socio-demographic characteristics, chronic medical conditions, obstetric complications and family history in both the current and previous pregnancy. In this cohort, 66% of stillbirths were observed for multiparous women. The best performing classifier (XGBoost) predicted 45% (95% CI: 43%, 46%) of stillbirths for all women and 45% (95% CI: 43%, 47%) of stillbirths after the inclusion of previous pregnancy history. Almost half of stillbirths could be potentially identified antenatally based on a combination of current pregnancy complications, congenital anomalies, maternal characteristics, and medical history. Greatest sensitivity is achieved with addition of current pregnancy complications. Ensemble classifiers offered marginal improvement for prediction compared to logistic regression.

Original languageEnglish
Article number5354
JournalScientific Reports
Volume10
Issue number1
DOIs
Publication statusPublished - 1 Dec 2020

Fingerprint Dive into the research topics of 'Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015'. Together they form a unique fingerprint.

  • Cite this

    Malacova, E., Tippaya, S., Bailey, H. D., Chai, K., Farrant, B. M., Gebremedhin, A. T., Leonard, H., Marinovich, M. L., Nassar, N., Phatak, A., Raynes-Greenow, C., Regan, A. K., Shand, A. W., Shepherd, C. C. J., Srinivasjois, R., Tessema, G. A., & Pereira, G. (2020). Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015. Scientific Reports, 10(1), [5354]. https://doi.org/10.1038/s41598-020-62210-9