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

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 singl...

Full description

Bibliographic Details
Main Authors: Malacova, Eva, Tippaya, Sawitchaya, Bailey, Helen, Chai, Kevin, Farrant, B.M., Gebremedhin, Amanuel, Leonard, H., Marinovich, Luke, Nassar, N., Phatak, Aloke, Raynes-Greenow, C., Regan, Annette, Shand, A.W., Shepherd, Carrington, Srinivasjois, Ravisha, Tessema, Gizachew, Pereira, Gavin
Format: Journal Article
Language:English
Published: NATURE PORTFOLIO 2020
Subjects:
Online Access:http://purl.org/au-research/grants/arc/IC180100030
http://hdl.handle.net/20.500.11937/90949
_version_ 1848765469531570176
author Malacova, Eva
Tippaya, Sawitchaya
Bailey, Helen
Chai, Kevin
Farrant, B.M.
Gebremedhin, Amanuel
Leonard, H.
Marinovich, Luke
Nassar, N.
Phatak, Aloke
Raynes-Greenow, C.
Regan, Annette
Shand, A.W.
Shepherd, Carrington
Srinivasjois, Ravisha
Tessema, Gizachew
Pereira, Gavin
author_facet Malacova, Eva
Tippaya, Sawitchaya
Bailey, Helen
Chai, Kevin
Farrant, B.M.
Gebremedhin, Amanuel
Leonard, H.
Marinovich, Luke
Nassar, N.
Phatak, Aloke
Raynes-Greenow, C.
Regan, Annette
Shand, A.W.
Shepherd, Carrington
Srinivasjois, Ravisha
Tessema, Gizachew
Pereira, Gavin
author_sort Malacova, Eva
building Curtin Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-14T11:35:45Z
format Journal Article
id curtin-20.500.11937-90949
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:35:45Z
publishDate 2020
publisher NATURE PORTFOLIO
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-909492023-05-04T08:13:55Z Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015 Malacova, Eva Tippaya, Sawitchaya Bailey, Helen Chai, Kevin Farrant, B.M. Gebremedhin, Amanuel Leonard, H. Marinovich, Luke Nassar, N. Phatak, Aloke Raynes-Greenow, C. Regan, Annette Shand, A.W. Shepherd, Carrington Srinivasjois, Ravisha Tessema, Gizachew Pereira, Gavin Science & Technology Multidisciplinary Sciences Science & Technology - Other Topics Algorithms Cohort Studies Female Humans Live Birth Machine Learning Maternal Age Pregnancy Pregnancy Complications Prenatal Care Reproductive History Risk Assessment Socioeconomic Factors Stillbirth Western Australia Humans Pregnancy Complications Reproductive History Prenatal Care Risk Assessment Cohort Studies Maternal Age Pregnancy Algorithms Socioeconomic Factors Western Australia Female Stillbirth Live Birth Machine Learning 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. 2020 Journal Article http://hdl.handle.net/20.500.11937/90949 10.1038/s41598-020-62210-9 English http://purl.org/au-research/grants/arc/IC180100030 http://purl.org/au-research/grants/nhmrc/1099655 http://purl.org/au-research/grants/nhmrc/1173991 http://creativecommons.org/licenses/by/4.0/ NATURE PORTFOLIO fulltext
spellingShingle Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
Algorithms
Cohort Studies
Female
Humans
Live Birth
Machine Learning
Maternal Age
Pregnancy
Pregnancy Complications
Prenatal Care
Reproductive History
Risk Assessment
Socioeconomic Factors
Stillbirth
Western Australia
Humans
Pregnancy Complications
Reproductive History
Prenatal Care
Risk Assessment
Cohort Studies
Maternal Age
Pregnancy
Algorithms
Socioeconomic Factors
Western Australia
Female
Stillbirth
Live Birth
Machine Learning
Malacova, Eva
Tippaya, Sawitchaya
Bailey, Helen
Chai, Kevin
Farrant, B.M.
Gebremedhin, Amanuel
Leonard, H.
Marinovich, Luke
Nassar, N.
Phatak, Aloke
Raynes-Greenow, C.
Regan, Annette
Shand, A.W.
Shepherd, Carrington
Srinivasjois, Ravisha
Tessema, Gizachew
Pereira, Gavin
Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title_full Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title_fullStr Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title_full_unstemmed Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title_short Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
title_sort stillbirth risk prediction using machine learning for a large cohort of births from western australia, 1980–2015
topic Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
Algorithms
Cohort Studies
Female
Humans
Live Birth
Machine Learning
Maternal Age
Pregnancy
Pregnancy Complications
Prenatal Care
Reproductive History
Risk Assessment
Socioeconomic Factors
Stillbirth
Western Australia
Humans
Pregnancy Complications
Reproductive History
Prenatal Care
Risk Assessment
Cohort Studies
Maternal Age
Pregnancy
Algorithms
Socioeconomic Factors
Western Australia
Female
Stillbirth
Live Birth
Machine Learning
url http://purl.org/au-research/grants/arc/IC180100030
http://purl.org/au-research/grants/arc/IC180100030
http://purl.org/au-research/grants/arc/IC180100030
http://hdl.handle.net/20.500.11937/90949