{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T18:58:50Z","timestamp":1775933930647,"version":"3.50.1"},"reference-count":41,"publisher":"Georg Thieme Verlag KG","issue":"10","funder":[{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063036"],"award-info":[{"award-number":["U10 HD063036"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063072"],"award-info":[{"award-number":["U10 HD063072"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063047"],"award-info":[{"award-number":["U10 HD063047"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063037"],"award-info":[{"award-number":["U10 HD063037"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063041"],"award-info":[{"award-number":["U10 HD063041"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063020"],"award-info":[{"award-number":["U10 HD063020"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063046"],"award-info":[{"award-number":["U10 HD063046"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063048"],"award-info":[{"award-number":["U10 HD063048"]}]},{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","award":["U10 HD063053"],"award-info":[{"award-number":["U10 HD063053"]}]},{"name":"Clinical and Translational Science Institutes","award":["UL1TR001108"],"award-info":[{"award-number":["UL1TR001108"]}]},{"name":"Clinical and Translational Science Institutes","award":["UL1TR000153"],"award-info":[{"award-number":["UL1TR000153"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Am J Perinatol"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This study aimed to develop machine learning (ML) models for predicting preterm preeclampsia using the information available before 23 weeks gestation.<\/jats:p><jats:p>This was a secondary analysis of the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) cohort. We considered 131 features available before 23 weeks including maternal demographics, obstetrics and family history, social determinants of health, physical activity, nutrition, and early second-trimester ultrasound. Our primary outcome was preterm preeclampsia before 37 weeks. The dataset was randomly split into a training set (70%) and a validation set (30%). ML models using glmnet, multilayer perceptron, random forest, XGBoost (extreme gradient boosting), and LightGBM models were developed. Using the ML approach that achieved the best area under the curve (AUC), we developed the final model. Further feature selection was conducted from the top 25 important features based on SHapley Additive exPlanations (SHAP) values. The performance of the final model was assessed using the validation dataset.<\/jats:p><jats:p>Of 9,467 individuals, 219 (2.3%) had preterm preeclampsia. The AUC of the XGBoost model was the highest (AUC\u2009=\u20090.749 [95% confidence interval (95% CI), 0.736\u20130.762]) compared with other models. Therefore, XGBoost was used to develop models using fewer variables. The XGBoost model with the eight features (in order of importance: mean uterine artery pulsatility index in the early second trimester, chronic hypertension, pregestational diabetes, uterine artery notch, systolic and diastolic blood pressure in the first trimester, body mass index, and maternal age) was chosen as the final model as it had an AUC of 0.741 (95% CI, 0.730\u20130.752) which was not inferior to the original model (p\u2009=\u20090.58). The final model in the validation dataset had an AUC of 0.779 (95% CI, 0.722\u20130.831). An online application of the final model was developed (\n                     https:\/\/kawakita.shinyapps.io\/Preterm_preeclampsia\/\n                  ).<\/jats:p><jats:p>ML algorithms using information available before 23 weeks can accurately predict preterm preeclampsia before 37 weeks.<\/jats:p>","DOI":"10.1055\/a-2495-3600","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:44:14Z","timestamp":1733359454000},"page":"1354-1361","source":"Crossref","is-referenced-by-count":4,"title":["Derivation and Validation of Prediction of Preterm Preeclampsia Using Machine Learning Algorithms"],"prefix":"10.1055","volume":"42","author":[{"given":"Tetsuya","family":"Kawakita","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juliana G.","family":"Martins","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yara H.","family":"Diab","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lea","family":"Nehme","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saade","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"194","published-online":{"date-parts":[[2024,12,24]]},"reference":[{"issue":"01","key":"ref1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejogrb.2013.05.005","article-title":"Global and regional estimates of preeclampsia and eclampsia: a systematic review","volume":"170","author":"E Abalos","year":"2013","journal-title":"Eur J Obstet Gynecol Reprod Biol"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"f6564","DOI":"10.1136\/bmj.f6564","article-title":"Pre-eclampsia rates in the United States, 1980-2010: age-period-cohort analysis","volume":"347","author":"C V Ananth","year":"2013","journal-title":"BMJ"},{"issue":"04","key":"ref3","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1097\/AOG.0000000000000472","article-title":"Maternal morbidity associated with early-onset and late-onset preeclampsia","volume":"124","author":"S Lisonkova","year":"2014","journal-title":"Obstet Gynecol"},{"issue":"03","key":"ref4","first-page":"283","article-title":"Racial\/ethnic differences in pregnancy-related hypertensive disease in nulliparous women","volume":"24","author":"G Ghosh","year":"2014","journal-title":"Ethn Dis"},{"issue":"01","key":"ref5","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1097\/AOG.0b013e31821fd49d","article-title":"Changes in pregnancy mortality ascertainment: United States, 1999-2005","volume":"118","author":"A P MacKay","year":"2011","journal-title":"Obstet Gynecol"},{"issue":"02","key":"ref6","first-page":"1","article-title":"Pregnancy-related mortality surveillance\u2013United States, 1991\u20131999","volume":"52","author":"J Chang","year":"2003","journal-title":"MMWR Surveill Summ"},{"issue":"06","key":"ref7","first-page":"950","article-title":"Preeclampsia and fetal growth","volume":"96","author":"R A Odeg\u00e5rd","year":"2000","journal-title":"Obstet Gynecol"},{"issue":"01","key":"ref8","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1053\/sper.2002.29838","article-title":"Maternal medical disease: risk of antepartum fetal death","volume":"26","author":"L L Simpson","year":"2002","journal-title":"Semin Perinatol"},{"issue":"06","key":"ref9","doi-asserted-by":"crossref","first-page":"544.e1","DOI":"10.1016\/j.ajog.2013.08.019","article-title":"Incidence of preeclampsia: risk factors and outcomes associated with early- versus late-onset disease","volume":"209","author":"S Lisonkova","year":"2013","journal-title":"Am J Obstet Gynecol"},{"issue":"7323","key":"ref10","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1136\/bmj.323.7323.1213","article-title":"Long term mortality of mothers and fathers after pre-eclampsia: population based cohort study","volume":"323","author":"H U Irgens","year":"2001","journal-title":"BMJ"},{"issue":"03","key":"ref11","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1002\/uog.5252","article-title":"Prediction of pre-eclampsia by uterine artery Doppler imaging: relationship to gestational age at delivery and small-for-gestational age","volume":"31","author":"C K Yu","year":"2008","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"03","key":"ref12","doi-asserted-by":"crossref","first-page":"287.e1","DOI":"10.1016\/j.ajog.2016.12.029","article-title":"Failure of physiologic transformation of spiral arteries, endothelial and trophoblast cell activation, and acute atherosis in the basal plate of the placenta","volume":"216","author":"C A Labarrere","year":"2017","journal-title":"Am J Obstet Gynecol"},{"issue":"02","key":"ref13","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1093\/aje\/kwj354","article-title":"Previous preeclampsia, preterm delivery, and delivery of a small for gestational age infant and the risk of unexplained stillbirth in the second pregnancy: a retrospective cohort study, Scotland, 1992-2001","volume":"165","author":"G C Smith","year":"2007","journal-title":"Am J Epidemiol"},{"issue":"03","key":"ref14","doi-asserted-by":"crossref","first-page":"e0230483","DOI":"10.1371\/journal.pone.0230483","article-title":"Early and late onset pre-eclampsia and small for gestational age risk in subsequent pregnancies","volume":"15","author":"T P Bernardes","year":"2020","journal-title":"PLoS One"},{"issue":"02","key":"ref15","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1002\/uog.19112","article-title":"Screening for pre-eclampsia by maternal factors and biomarkers at 11-13\u2009weeks' gestation","volume":"52","author":"M Y Tan","year":"2018","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"05","key":"ref16","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1002\/uog.13275","article-title":"First-trimester uterine artery Doppler and adverse pregnancy outcome: a meta-analysis involving 55,974 women","volume":"43","author":"L Velauthar","year":"2014","journal-title":"Ultrasound Obstet Gynecol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"103780","DOI":"10.1016\/j.ebiom.2021.103780","article-title":"Clinical tools and biomarkers to predict preeclampsia","volume":"75","author":"T M MacDonald","year":"2022","journal-title":"EBioMedicine"},{"issue":"03","key":"ref18","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1002\/uog.19099","article-title":"Management of pregnancies after combined screening for pre-eclampsia at 19-24\u2009weeks' gestation","volume":"52","author":"M Litwinska","year":"2018","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"04","key":"ref19","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1002\/uog.19111","article-title":"Screening for pre-eclampsia at 35-37\u2009weeks' gestation","volume":"52","author":"A Panaitescu","year":"2018","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"03","key":"ref20","doi-asserted-by":"crossref","first-page":"497.e1","DOI":"10.1016\/j.ajog.2022.03.064","article-title":"Placental protein levels in maternal serum are associated with adverse pregnancy outcomes in nulliparous patients","volume":"227","author":"S Parry","year":"2022","journal-title":"Am J Obstet Gynecol"},{"issue":"04","key":"ref21","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1097\/AOG.0000000000004706","article-title":"Introduction to machine learning in obstetrics and gynecology","volume":"139","author":"S A Shazly","year":"2022","journal-title":"Obstet Gynecol"},{"issue":"04","key":"ref22","doi-asserted-by":"crossref","first-page":"539.e1","DOI":"10.1016\/j.ajog.2015.01.019","article-title":"A description of the methods of the Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be (nuMoM2b)","volume":"212","author":"D M Haas","year":"2015","journal-title":"Am J Obstet Gynecol"},{"key":"ref24","volume-title":"Neural networks: a systematic introduction","author":"R Rojas","year":"2013","edition":"1st ed."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"3761203","DOI":"10.1155\/2019\/3761203","article-title":"A lightGBM-based EEG analysis method for driver mental states classification","volume":"2019","author":"H Zeng","year":"2019","journal-title":"Comput Intell Neurosci"},{"key":"ref28","first-page":"3146","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"G Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","volume-title":"Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating","author":"E W Steyerberg","year":"2019"},{"issue":"03","key":"ref30","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2009.187","article-title":"Sensitivity analysis of kappa-fold cross validation in prediction error estimation","volume":"32","author":"J D Rodr\u00edguez","year":"2010","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"09","key":"ref33","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1056\/NEJMms2004740","article-title":"Hidden in plain sight\u2014reconsidering the use of race correction in clinical algorithms","volume":"383","author":"D A Vyas","year":"2020","journal-title":"N Engl J Med"},{"issue":"01","key":"ref34","doi-asserted-by":"crossref","first-page":"e44","DOI":"10.1097\/AOG.0000000000002708","article-title":"ACOG Committee Opinion No. 743: Low-dose aspirin use during pregnancy","volume":"132","author":"American College of Obstetricians and Gynecologists","year":"2018","journal-title":"Obstet Gynecol"},{"issue":"03","key":"ref35","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"E R DeLong","year":"1988","journal-title":"Biometrics"},{"issue":"01","key":"ref36","doi-asserted-by":"crossref","first-page":"25","DOI":"10.4097\/kja.21209","article-title":"Receiver operating characteristic curve: overview and practical use for clinicians","volume":"75","author":"F S Nahm","year":"2022","journal-title":"Korean J Anesthesiol"},{"issue":"06","key":"ref37","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"A J Vickers","year":"2006","journal-title":"Med Decis Making"},{"issue":"01","key":"ref38","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1097\/01.ede.0000147512.81966.ba","article-title":"Optimal cut-point and its corresponding Youden Index to discriminate individuals using pooled blood samples","volume":"16","author":"E F Schisterman","year":"2005","journal-title":"Epidemiology"},{"issue":"03","key":"ref39","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1002\/ijgo.14049","article-title":"Routine first trimester combined screening for preterm preeclampsia in Australia: a multicenter clinical implementation cohort study","volume":"158","author":"D L Rolnik","year":"2022","journal-title":"Int J Gynaecol Obstet"},{"issue":"04","key":"ref40","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1002\/uog.23645","article-title":"Prospective evaluation of first-trimester screening strategy for preterm pre-eclampsia and its clinical applicability in China","volume":"58","author":"J Hu","year":"2021","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"03","key":"ref41","first-page":"1","article-title":"Timing and adequacy of prenatal care in the United States, 2016","volume":"67","author":"M JK Osterman","year":"2018","journal-title":"Natl Vital Stat Rep"},{"issue":"01","key":"ref42","doi-asserted-by":"crossref","first-page":"31","DOI":"10.2105\/AJPH.83.1.31","article-title":"A comparison of prenatal care use in the United States and Europe","volume":"83","author":"P Buekens","year":"1993","journal-title":"Am J Public Health"},{"issue":"05","key":"ref43","doi-asserted-by":"crossref","first-page":"594.e1","DOI":"10.1016\/j.ajog.2017.06.013","article-title":"Role of early second-trimester uterine artery Doppler screening to predict small-for-gestational-age babies in nulliparous women","volume":"217","author":"S Parry","year":"2017","journal-title":"Am J Obstet Gynecol"},{"issue":"10","key":"ref44","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1001\/jama.2017.1373","article-title":"Predictive accuracy of serial transvaginal cervical lengths and quantitative vaginal fetal fibronectin levels for spontaneous preterm birth among nulliparous women","volume":"317","author":"M S Esplin","year":"2017","journal-title":"JAMA"},{"issue":"02","key":"ref45","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1177\/0969141318797961","article-title":"Fewer women aged 35 and older choose serum screening for Down's syndrome: impact and implications","volume":"26","author":"G Lambert-Messerlian","year":"2019","journal-title":"J Med Screen"}],"container-title":["American Journal of Perinatology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-2495-3600.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:32:21Z","timestamp":1751927541000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-2495-3600"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"references-count":41,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,7,7]]},"published-print":{"date-parts":[[2025,7]]}},"URL":"https:\/\/doi.org\/10.1055\/a-2495-3600","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["0735-1631","1098-8785"],"issn-type":[{"value":"0735-1631","type":"print"},{"value":"1098-8785","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12,4]]},"published":{"date-parts":[[2024,12,4]]}}}