Show simple item record

dc.contributor.authorMalacova, Eva
dc.contributor.authorTippaya, Sawitchaya
dc.contributor.authorBailey, Helen
dc.contributor.authorChai, Kevin
dc.contributor.authorFarrant, B.M.
dc.contributor.authorGebremedhin, Amanuel
dc.contributor.authorLeonard, H.
dc.contributor.authorMarinovich, Luke
dc.contributor.authorNassar, N.
dc.contributor.authorPhatak, Aloke
dc.contributor.authorRaynes-Greenow, C.
dc.contributor.authorRegan, Annette
dc.contributor.authorShand, A.W.
dc.contributor.authorShepherd, Carrington
dc.contributor.authorSrinivasjois, Ravisha
dc.contributor.authorTessema, Gizachew
dc.contributor.authorPereira, Gavin
dc.date.accessioned2023-03-14T08:10:27Z
dc.date.available2023-03-14T08:10:27Z
dc.date.issued2020
dc.identifier.citationMalacova, E. and Tippaya, S. and Bailey, H.D. and Chai, K. and Farrant, B.M. and Gebremedhin, A.T. and Leonard, H. et al. 2020. Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015. Scientific Reports. 10 (1): pp. 5354-5354.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/90949
dc.identifier.doi10.1038/s41598-020-62210-9
dc.description.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.

dc.languageEnglish
dc.publisherNATURE PORTFOLIO
dc.relation.sponsoredbyhttp://purl.org/au-research/grants/arc/IC180100030
dc.relation.sponsoredbyhttp://purl.org/au-research/grants/nhmrc/1099655
dc.relation.sponsoredbyhttp://purl.org/au-research/grants/nhmrc/1173991
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectScience & Technology
dc.subjectMultidisciplinary Sciences
dc.subjectScience & Technology - Other Topics
dc.subjectAlgorithms
dc.subjectCohort Studies
dc.subjectFemale
dc.subjectHumans
dc.subjectLive Birth
dc.subjectMachine Learning
dc.subjectMaternal Age
dc.subjectPregnancy
dc.subjectPregnancy Complications
dc.subjectPrenatal Care
dc.subjectReproductive History
dc.subjectRisk Assessment
dc.subjectSocioeconomic Factors
dc.subjectStillbirth
dc.subjectWestern Australia
dc.subjectHumans
dc.subjectPregnancy Complications
dc.subjectReproductive History
dc.subjectPrenatal Care
dc.subjectRisk Assessment
dc.subjectCohort Studies
dc.subjectMaternal Age
dc.subjectPregnancy
dc.subjectAlgorithms
dc.subjectSocioeconomic Factors
dc.subjectWestern Australia
dc.subjectFemale
dc.subjectStillbirth
dc.subjectLive Birth
dc.subjectMachine Learning
dc.titleStillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980–2015
dc.typeJournal Article
dcterms.source.volume10
dcterms.source.number1
dcterms.source.startPage5354
dcterms.source.endPage5354
dcterms.source.issn2045-2322
dcterms.source.titleScientific Reports
dc.date.updated2023-03-14T08:10:27Z
curtin.departmentSchool of Public Health
curtin.departmentCurtin Medical School
curtin.departmentSchool of Elec Eng, Comp and Math Sci (EECMS)
curtin.accessStatusOpen access
curtin.facultyFaculty of Health Sciences
curtin.facultyFaculty of Science and Engineering
curtin.contributor.orcidPhatak, Aloke [0000-0002-0637-7461]
curtin.contributor.orcidPereira, Gavin [0000-0003-3740-8117]
curtin.contributor.orcidMarinovich, Luke [0000-0002-3801-8180]
curtin.contributor.orcidRegan, Annette [0000-0002-3879-6193]
curtin.contributor.orcidTessema, Gizachew [0000-0002-4784-8151]
curtin.contributor.orcidChai, Kevin [0000-0003-1645-0922]
curtin.contributor.orcidShepherd, Carrington [0000-0003-0043-7053]
curtin.contributor.orcidBailey, Helen [0000-0002-1259-3793]
curtin.contributor.researcheridPhatak, Aloke [D-5166-2009]
curtin.contributor.researcheridPereira, Gavin [D-7136-2014]
curtin.contributor.researcheridTessema, Gizachew [J-9235-2018]
curtin.contributor.researcheridChai, Kevin [F-1015-2013]
curtin.contributor.researcheridBailey, Helen [G-6167-2017]
curtin.identifier.article-numberARTN 5354
dcterms.source.eissn2045-2322
curtin.contributor.scopusauthoridPhatak, Aloke [57188762833] [7005067216]
curtin.contributor.scopusauthoridPereira, Gavin [35091486200]
curtin.contributor.scopusauthoridMalacova, Eva [16242025400]
curtin.contributor.scopusauthoridRegan, Annette [25932252200]
curtin.contributor.scopusauthoridChai, Kevin [23396028100]
curtin.contributor.scopusauthoridShepherd, Carrington [55012496100]
curtin.contributor.scopusauthoridBailey, Helen [7103338719]
curtin.contributor.scopusauthoridGebremedhin, Amanuel [56412162800]
curtin.repositoryagreementV3


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/