{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T21:51:19Z","timestamp":1794433879597,"version":"4.9.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>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.<\/jats:p>","DOI":"10.1038\/s41598-020-62210-9","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T07:06:27Z","timestamp":1585033587000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980\u20132015"],"prefix":"10.1038","volume":"10","author":[{"given":"Eva","family":"Malacova","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sawitchaya","family":"Tippaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen D.","family":"Bailey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3903-0990","authenticated-orcid":false,"given":"Brad M.","family":"Farrant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amanuel T.","family":"Gebremedhin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Leonard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Marinovich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natasha","family":"Nassar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0637-7461","authenticated-orcid":false,"given":"Aloke","family":"Phatak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camille","family":"Raynes-Greenow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annette K.","family":"Regan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonia W.","family":"Shand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carrington C. J.","family":"Shepherd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravisha","family":"Srinivasjois","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gizachew A.","family":"Tessema","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gavin","family":"Pereira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,3,24]]},"reference":[{"key":"62210_CR1","unstructured":"Australian Institute of Health and Welfare. Perinatal deaths in Australia: 2013-2014. AIHW Cat. no. PER 94 (2018)."},{"key":"62210_CR2","unstructured":"Monk, A. et al. Perinatal deaths in Australia, 1993-2012. Australian Institute of Health and Welfare Perinatal deaths series no. 1 Cat. no. PER 86 (2016)."},{"key":"62210_CR3","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1016\/S0140-6736(10)62233-7","volume":"377","author":"V Flenady","year":"2011","unstructured":"Flenady, V. et al. Major risk factors for stillbirth in high-income countries: a systematic review and meta-analysis. The Lancet 377, 1331\u20131340 (2011).","journal-title":"The Lancet"},{"key":"62210_CR4","doi-asserted-by":"crossref","unstructured":"Goldenberg, R. L. et al. Stillbirths: the vision for 2020. The Lancet 377 (2011).","DOI":"10.1016\/S0140-6736(10)62235-0"},{"key":"62210_CR5","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1002\/uog.17288","volume":"48","author":"R Akolekar","year":"2016","unstructured":"Akolekar, R., Machuca, M., Mendes, M., Paschos, D. V. & Nicolaides, K. H. Prediction of stillbirth from placental growth factor at 11\u201313 weeks. Ultrasound in Obstetrics & Gynecology 48, 618\u2013623 (2016).","journal-title":"Ultrasound in Obstetrics & Gynecology"},{"key":"62210_CR6","doi-asserted-by":"crossref","unstructured":"Akolekar, R., Tokunanka, M., Ortega, A. N., Syngelaki, A. & Nicolaides, K. H. Prediction of stillbirth from maternal factors, fetal biometry and uterine artery Doppler at 19\u201324 weeks. Ultrasound in Obstetrics and Gynecology 48 (2016).","DOI":"10.1002\/uog.17295"},{"key":"62210_CR7","doi-asserted-by":"crossref","unstructured":"Kayode, G. A. et al. Predicting stillbirth in a low resource setting. BMC Pregnancy & Childbirth 16 (2016).","DOI":"10.1186\/s12884-016-1061-2"},{"key":"62210_CR8","doi-asserted-by":"publisher","first-page":"e0173461","DOI":"10.1371\/journal.pone.0173461","volume":"12","author":"AS Trudell","year":"2017","unstructured":"Trudell, A. S., Tuuli, M. G., Colditz, G. A., Macones, G. A. & Odibo, A. O. A stillbirth calculator: Development and internal validation of a clinical prediction model to quantify stillbirth risk. PLoS One 12, e0173461 (2017).","journal-title":"PLoS One"},{"key":"62210_CR9","doi-asserted-by":"crossref","unstructured":"Yerlikaya, G., Akolekar, R., McPherson, K., Syngelaki, A. & H., N. K. Prediction of stillbirth from maternal demographic and pregnancy characteristics. Ultrasound in Obstetrics and Gynecology 48 (2016).","DOI":"10.1002\/uog.17290"},{"key":"62210_CR10","doi-asserted-by":"crossref","unstructured":"Mastrodima, S., Akolekar, R., Yerlikaya, G., Tzelepis, T. & Nicolaides, K. Prediction of stillbirth from biochemical and biophysical markers at 11-13 weeks. Ultrasound in obstetrics & gynecology 48 (2016).","DOI":"10.1002\/uog.17289"},{"key":"62210_CR11","unstructured":"Royal College of Obstetricians and Gynaecologists. The investigation and management of the small\u2013for\u2013gestational\u2013age fetus. Royal College of Obstetricians and Gynaecologists Guidline No.31 (2014)."},{"key":"62210_CR12","doi-asserted-by":"crossref","unstructured":"Society for Maternal- Fetal Medicine Publications. The choice of progesterone for the prevention of preterm birth in women with singleton pregnancy and prior preterm birth American Journal of Obsterics and Gynaecology 216 (2017).","DOI":"10.1016\/j.ajog.2017.01.022"},{"key":"62210_CR13","doi-asserted-by":"crossref","unstructured":"Roberge, S., Demers, S. & Bujold, E. Antiplatelet therapy before or after 16 weeks\u2019 gestation for preventing preeclamspia. American Journal of Obsterics and Gynaecologists 216 (2017).","DOI":"10.1016\/j.ajog.2017.01.034"},{"key":"62210_CR14","unstructured":"Sentilhes, L. et al. Prevention of spontaneous preterm birth: Guidlines for clinical practice from the French College of Gynaecologists and Obstetricians (CNGOF). European Journal of Obstetrics and Gynaecology and Reproductive Biology 210 (2017)."},{"key":"62210_CR15","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-017-4742-5","volume":"17","author":"H Blencowe","year":"2017","unstructured":"Blencowe, H., Chou, V. B., Lawn, J. E. & Bhutta, Z. A. Modelling stillbirth mortality reduction with the Lives Saved Tool. BMC public health 17, 784 (2017).","journal-title":"BMC public health"},{"key":"62210_CR16","doi-asserted-by":"crossref","unstructured":"Adrian, S., Ben-Shlomo, Y., Blom, A. W. & Steele, F. Probabilistic record linkage International Journal of Epidemiology 45 (2016).","DOI":"10.1093\/ije\/dyv322"},{"key":"62210_CR17","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1111\/j.1467-842X.1999.tb01297.x","volume":"23","author":"CDAJ Holman","year":"1999","unstructured":"Holman, C. D. A. J., Bass, A. J., Rouse, I. L. & Hobbs, M. S. T. Population-based linkage of health records in Western Australia: development of a health services research linked database. Australian and New Zealand Journal of Public Health 23, 453\u2013459 (1999).","journal-title":"Australian and New Zealand Journal of Public Health"},{"key":"62210_CR18","unstructured":"Australian Bureau of Statistics. Socio-Economic Indexes for Areas (SEIFA) ABS (2011)."},{"key":"62210_CR19","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011)."},{"key":"62210_CR20","unstructured":"Lee, S.-I., Lee, H., Abbeel, P. & Ng, A. Y. Efficient L1 Regularized Logistic Regression. The 21st AAAI Conference on Artificial Intelligence Boston, USA (2006)."},{"key":"62210_CR21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random Forests. Machine Learning 45, 5\u201332 (2001).","journal-title":"Machine Learning"},{"key":"62210_CR22","doi-asserted-by":"crossref","unstructured":"Blagus, R. & Lusa, L. Boosting for high-dimensional two-class prediction. BMC Bioinformatics 16 (2015).","DOI":"10.1186\/s12859-015-0723-9"},{"key":"62210_CR23","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R. & Friedman, J. H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer New York (2009).","DOI":"10.1007\/978-0-387-84858-7"},{"key":"62210_CR24","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794 (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"62210_CR25","doi-asserted-by":"crossref","unstructured":"Aguiar, F. S. et al. Development of two artificial neural network models to support the diagnosis of pulmonary tuberculosis in hospitalized patients in Rio de Janeiro, Brazil. Medical & Biological Engineering & Computing 54 (2016).","DOI":"10.1007\/s11517-016-1465-1"},{"key":"62210_CR26","first-page":"1137","volume":"2","author":"R Kohavi","year":"1995","unstructured":"Kohavi, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the 14th International Joint Conference on Artificial intelligence 2, 1137\u20131143 (1995).","journal-title":"Proceedings of the 14th International Joint Conference on Artificial intelligence"},{"key":"62210_CR27","unstructured":"Buitinck, L. et al. API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv:1309.0238 (2013)."},{"key":"62210_CR28","unstructured":"Downey, F. Validation study of the Western Australian Midwives\u2019 Notification System: 2005 Birth Data. Department of Health Western Australia Statistical series number 78 (2007)."},{"key":"62210_CR29","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1111\/1471-0528.14971","volume":"125","author":"HE Reinebrant","year":"2017","unstructured":"Reinebrant, H. E. et al. Making stillbirths visible: a systematic reivew of globally reported causes of stillbirth. BJOG: an international journal of obstetrics and gynaecology 125, 212\u2013224 (2017).","journal-title":"BJOG: an international journal of obstetrics and gynaecology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-62210-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-62210-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-62210-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T03:51:36Z","timestamp":1670298696000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-62210-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,24]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["62210"],"URL":"https:\/\/doi.org\/10.1038\/s41598-020-62210-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,24]]},"assertion":[{"value":"19 September 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5354"}}