{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:44:29Z","timestamp":1791499469252,"version":"4.3.4"},"reference-count":45,"publisher":"American Medical Association (AMA)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Preeclampsia is a leading cause of maternal and perinatal morbidity and mortality, yet its unpredictable onset and rapid progression hinder timely management. Existing prediction tools often rely on specialized biomarkers, static assessments, or limited study cohorts, impeding clinical utility and generalizability.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To develop and validate machine learning models for dynamic, short-term prediction of preeclampsia onset using longitudinal electronic health record (EHR) data.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This retrospective, multisite cohort study included pregnancies delivered between October 1, 2020, and May 31, 2025, at 3 NewYork-Presbyterian hospitals: Weill Cornell Medical College (WCMC), Lower Manhattan Hospital (LMH), and Brooklyn Methodist Hospital (BMH). Extreme gradient boosting models were developed to predict preeclampsia onset within 1, 2, and 4 weeks. Performance was assessed using nested cross-validation at the training site and external validation via direct transfer, fine-tuning, and retraining. The study included pregnancies among individuals 18 years or older (35\u202f895 at WCMC, 8664 at LMH, and 14 280 at BMH).<\/jats:p>\n <\/jats:sec>\n \n Exposure<\/jats:title>\n Routine information captured within the EHR, including blood pressure, maternal characteristics and routine laboratory test results.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n The main outcome was development of preeclampsia within specified prediction windows. Model performance was evaluated using area under the receiver operating characteristic curve, specificity and positive predictive value at 90% sensitivity.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Among 58 839 pregnancies (mean [SD] maternal age, 33.3 [5.3] years; 10 196 [17.3%] Asian, 6525 [11.1%] Black or African American, 32 675 [55.5%] White, and 9443 [16.0%] other [ie, those who were races other than Asian, Black, or White] or unknown race), individuals who developed preeclampsia were older (median [IQR] age, 35.0 [31.0\u201338.0] vs 34.0 [31.0-37.0] years in the WCMC group [\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001], 35.0 [31.0\u201338.0] years vs 34.0 [32.0-37.0] years in the LMH group [\n P<\/jats:italic>\n \u2009=\u2009.003], and 33.0 [28.0\u201336.0] vs 31.0 [26.0\u201335.0] years in the BMH group [\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001]) and more frequently Black (335 of 2227 [15.0%] vs 2178 of 3668 [6.5%] in the WCMC group [\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001], 117 of 792 [14.8%] vs 566 of 7872 [7.2%] in the LMH group [\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001], and 455 of 1088 [41.8%] vs 2874 of 13,192 [21.8%] in the BMH group [\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001]). Predictive performance increased from 28 to 34 weeks\u2019 gestation and peaked at 34 weeks\u2019 gestation (areas under the receiver operating characteristic curves, 0.863 at training and 0.808-0.834 at validation). The positive predictive values increased from approximately 0.001 to 0.002 at 28 weeks to peak values at 36 weeks (mean [SD], 0.057 [0.012] at LMH and 0.046 [0.007] at BMH), whereas the negative predictive values were greater than 0.993. Blood pressure was the most informative predictor, whereas laboratory measures (including albumin, alkaline phosphatase, and hematologic indexes) contributed to earlier gestation, with demographic and obstetric factors increasing in importance later.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this retrospective, multisite cohort study of pregnancies in late gestation, dynamic short-term prediction of preeclampsia was feasible using routinely available clinical and laboratory data. These results suggest that this approach provided opportunities for earlier intervention and would be adaptable across diverse health care settings.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2026.0359","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:30:22Z","timestamp":1772814622000},"page":"e260359","source":"Crossref","is-referenced-by-count":6,"title":["Machine Learning for Dynamic and Short-Term Prediction of Preeclampsia Using Routine Clinical Data"],"prefix":"10.1001","volume":"9","author":[{"given":"Haoyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Population Health Sciences, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxi","family":"Zang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weishen","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He S.","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tracy B.","family":"Grossman","sequence":"additional","affiliation":[{"name":"Division of Maternal-Fetal Medicine, NewYork-Presbyterian Brooklyn Methodist Hospital, Brooklyn, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, Weill Cornell Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"issue":"7","key":"zoi260029r1","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1161\/CIRCRESAHA.118.313276","article-title":"Preeclampsia: pathophysiology, challenges, and perspectives.","volume":"124","author":"Rana","year":"2019","journal-title":"Circ Res"},{"issue":"5","key":"zoi260029r2","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1373\/clinchem.2011.169094","article-title":"The promise of angiogenic markers for the early diagnosis and prediction of preeclampsia.","volume":"58","author":"Hagmann","year":"2012","journal-title":"Clin Chem"},{"issue":"4","key":"zoi260029r3","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3892\/ijmm.2023.5292","article-title":"Predictive value of the sFlt-1\/PlGF ratio in women with suspected preeclampsia: an update.","volume":"52","author":"Velegrakis","year":"2023","journal-title":"Int J Mol Med"},{"issue":"1","key":"zoi260029r4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1056\/NEJMoa1414838","article-title":"Predictive value of the sFlt-1:PlGF ratio in women with suspected preeclampsia.","volume":"374","author":"Zeisler","year":"2016","journal-title":"N Engl J Med"},{"issue":"25","key":"zoi260029r5","doi-asserted-by":"publisher","first-page":"8443","DOI":"10.1080\/14767058.2021.1978067","article-title":"Preeclampsia and postpartum mental health: mechanisms and clinical implications.","volume":"35","author":"Srajer","year":"2022","journal-title":"J Matern Fetal Neonatal Med"},{"issue":"4","key":"zoi260029r6","doi-asserted-by":"publisher","first-page":"501","DOI":"10.4103\/2249-4863.174265","article-title":"Diagnosis and management of preeclampsia in community settings in low and middle-income countries.","volume":"4","author":"Salam","year":"2015","journal-title":"J Family Med Prim Care"},{"issue":"12","key":"zoi260029r7","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.76095","article-title":"Prediction of preeclampsia using machine learning: a systematic review.","volume":"16","author":"Malik","year":"2024","journal-title":"Cureus"},{"issue":"3","key":"zoi260029r8","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1080\/20476965.2024.2435845","article-title":"Preeclampsia prediction via machine learning: a systematic literature review.","volume":"14","author":"\u00d6zcan","year":"2024","journal-title":"Health Syst (Basingstoke)"},{"issue":"5","key":"zoi260029r9","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.83961","article-title":"Artificial intelligence applications in obstetric risk prediction: a systematic review of machine learning models for preeclampsia.","volume":"17","author":"Mohamed Dkeen","year":"2025","journal-title":"Cureus"},{"issue":"7","key":"zoi260029r10","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11906-024-01297-1","article-title":"Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review.","volume":"26","author":"Tiruneh","year":"2024","journal-title":"Curr Hypertens Rep"},{"issue":"2","key":"zoi260029r11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajogmf.2020.100100","article-title":"Early prediction of preeclampsia via machine learning.","volume":"2","author":"Maric","year":"2020","journal-title":"Am J Obstet Gynecol MFM"},{"key":"zoi260029r12","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1345573","article-title":"Prediction model of preeclampsia using machine learning based methods: a population based cohort study in China.","volume":"15","author":"Li","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"4","key":"zoi260029r13","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1038\/s41591-025-03509-w","article-title":"Preeclampsia risk prediction from prenatal cell-free DNA screening.","volume":"31","author":"Adil","year":"2025","journal-title":"Nat Med"},{"issue":"5","key":"zoi260029r14","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1002\/uog.12264","article-title":"Prediction of early and late pre-eclampsia from maternal characteristics, uterine artery Doppler and markers of vasculogenesis during first trimester of pregnancy.","volume":"41","author":"Parra-Cordero","year":"2013","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"2","key":"zoi260029r15","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1002\/uog.3881","article-title":"Screening for pre-eclampsia and fetal growth restriction by uterine artery Doppler and PAPP-A at 11-14 weeks\u2019 gestation.","volume":"29","author":"Pilalis","year":"2007","journal-title":"Ultrasound Obstet Gynecol"},{"issue":"7898","key":"zoi260029r16","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1038\/s41586-022-04410-z","article-title":"Early prediction of preeclampsia in pregnancy with cell-free RNA.","volume":"602","author":"Moufarrej","year":"2022","journal-title":"Nature"},{"issue":"1","key":"zoi260029r17","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1093\/jalm\/jfaa149","article-title":"A critical review on the use of race in understanding racial disparities in preeclampsia.","volume":"6","author":"Fasanya","year":"2021","journal-title":"J Appl Lab Med"},{"issue":"2S","key":"zoi260029r18","doi-asserted-by":"publisher","first-page":"S876","DOI":"10.1016\/j.ajog.2020.07.038","article-title":"Does race or ethnicity play a role in the origin, pathophysiology, and outcomes of preeclampsia? an expert review of the literature.","volume":"226","author":"Johnson","year":"2022","journal-title":"Am J Obstet Gynecol"},{"issue":"1","key":"zoi260029r19","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s41746-022-00612-x","article-title":"Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data.","volume":"5","author":"Li","year":"2022","journal-title":"NPJ Digit Med"},{"key":"zoi260029r20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2015.02.018","article-title":"Competing risks model in screening for preeclampsia by maternal characteristics and medical history.","author":"Wright","year":"2015","journal-title":"Am J Obstet Gynecol"},{"key":"zoi260029r21","doi-asserted-by":"publisher","first-page":"S31","DOI":"10.4103\/sja.SJA_543_18","article-title":"The STROBE guidelines.","volume":"13","author":"Cuschieri","year":"2019","journal-title":"Saudi J Anaesth"},{"issue":"2","key":"zoi260029r22","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/BF01897163","article-title":"A study of standardization of variables in cluster analysis.","volume":"5","author":"Milligan","year":"1988","journal-title":"J Classif"},{"issue":"8","key":"zoi260029r24","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1097\/OGX.0b013e3182331028","article-title":"A critical review of early-onset and late-onset preeclampsia.","volume":"66","author":"Raymond","year":"2011","journal-title":"Obstet Gynecol Surv"},{"key":"zoi260029r25","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/4108271","article-title":"Early- and late-onset preeclampsia: a comprehensive cohort study of laboratory and clinical findings according to the new ISHHP criteria.","volume":"2019","author":"W\u00f3jtowicz","year":"2019","journal-title":"Int J Hypertens"},{"issue":"5","key":"zoi260029r26","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1161\/HYPERTENSIONAHA.108.117358","article-title":"Early and late preeclampsia: two different maternal hemodynamic states in the latent phase of the disease.","volume":"52","author":"Valensise","year":"2008","journal-title":"Hypertension"},{"issue":"4","key":"zoi260029r27","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.preghy.2013.06.002","article-title":"PRE-EMPT (PRE-eclampsia-Eclampsia Monitoring, Prevention and Treatment): a low and middle income country initiative to reduce the global burden of maternal, fetal and infant death and disease related to pre-eclampsia.","volume":"3","author":"von Dadelszen","year":"2013","journal-title":"Pregnancy Hypertens"},{"key":"zoi260029r28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.jri.2019.05.003","article-title":"High incidence of early onset preeclampsia is probably the rule and not the exception worldwide. 20th anniversary of the reunion workshop: a summary.","volume":"133","author":"Robillard","year":"2019","journal-title":"J Reprod Immunol"},{"key":"zoi260029r29","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.2147\/IJWH.S283239","article-title":"Reviewing accuracy of first trimester screening for preeclampsia using maternal factors and biomarkers.","volume":"14","author":"Malone","year":"2022","journal-title":"Int J Womens Health"},{"key":"zoi260029r30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2020.07.020","author":"Chaemsaithong","year":"2022","journal-title":"Am J Obstet Gynecol"},{"issue":"2 pt 1","key":"zoi260029r31","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1097\/AOG.0b013e3181e9322a","article-title":"Prevention of preeclampsia and intrauterine growth restriction with aspirin started in early pregnancy: a meta-analysis.","volume":"116","author":"Bujold","year":"2010","journal-title":"Obstet Gynecol"},{"issue":"5","key":"zoi260029r32","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.ajog.2017.12.238","article-title":"Meta-analysis on the effect of aspirin use for prevention of preeclampsia on placental abruption and antepartum hemorrhage.","volume":"218","author":"Roberge","year":"2018","journal-title":"Am J Obstet Gynecol"},{"issue":"15","key":"zoi260029r33","doi-asserted-by":"publisher","first-page":"4427","DOI":"10.3390\/jcm13154427","article-title":"Controversies and clarifications regarding the role of aspirin in preeclampsia prevention: a focused review.","volume":"13","author":"Rottenstreich","year":"2024","journal-title":"J Clin Med"},{"key":"zoi260029r34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2020.01.020","article-title":"A new model for screening for early-onset preeclampsia.","author":"Serra","year":"2020","journal-title":"Am J Obstet Gynecol"},{"key":"zoi260029r35","doi-asserted-by":"publisher","DOI":"10.1101\/2023.02.03.23285385","article-title":"Prediction of preeclampsia from clinical and genetic risk factors in early and late pregnancy using machine learning and polygenic risk scores.","author":"Kovacheva","year":"2023","journal-title":"medRxiv"},{"key":"zoi260029r36","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.preghy.2021.10.006","article-title":"Novelelectronic health records applied for prediction of pre-eclampsia: machine-learning algorithms.","volume":"26","author":"Li","year":"2021","journal-title":"Pregnancy Hypertens"},{"issue":"1","key":"zoi260029r37","doi-asserted-by":"publisher","first-page":"17973","DOI":"10.1038\/s41598-021-97465-3","article-title":"Routinely collected antenatal data for longitudinal prediction of preeclampsia in nulliparous women: a population-based study.","volume":"11","author":"Sandstr\u00f6m","year":"2021","journal-title":"Sci Rep"},{"issue":"6","key":"zoi260029r38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0323873","article-title":"Development and validation of an interpretable longitudinal preeclampsia risk prediction using machine learning.","volume":"20","author":"Eberhard","year":"2025","journal-title":"PLoS One"},{"key":"zoi260029r39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jri.2019.07.004","article-title":"The two-stage placental model of preeclampsia: an update.","volume":"134-135","author":"Staff","year":"2019","journal-title":"J Reprod Immunol"},{"key":"zoi260029r40","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.placenta.2022.07.014","article-title":"Placental dysfunction: the core mechanism for poor neurodevelopmental outcomes in the offspring of preeclampsia pregnancies.","volume":"126","author":"Liu","year":"2022","journal-title":"Placenta"},{"issue":"3","key":"zoi260029r41","doi-asserted-by":"publisher","first-page":"H582","DOI":"10.1152\/ajpheart.00170.2024","article-title":"Metabolic theory of preeclampsia: implications for maternal cardiovascular health.","volume":"327","author":"Manoharan","year":"2024","journal-title":"Am J Physiol Heart Circ Physiol"},{"key":"zoi260029r42","doi-asserted-by":"publisher","first-page":"l2381","DOI":"10.1136\/bmj.l2381","article-title":"Pre-eclampsia: pathophysiology and clinical implications.","volume":"366","author":"Burton","year":"2019","journal-title":"BMJ"},{"issue":"3","key":"zoi260029r43","first-page":"283","article-title":"Racial\/ethnic differences in pregnancy-related hypertensive disease in nulliparous women.","volume":"24","author":"Ghosh","year":"2014","journal-title":"Ethn Dis"},{"key":"zoi260029r44","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.933822","article-title":"Hypertensive disorders of pregnancy and cardiovascular disease risk across races and ethnicities: a review.","author":"Burger","year":"2022","journal-title":"Front Cardiovasc Med"},{"issue":"17","key":"zoi260029r45","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.121.021818","article-title":"Association between Black race, clinical severity, and management of acute pulmonary embolism: a retrospective cohort study.","volume":"10","author":"Phillips","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"zoi260029r23","author":"Chen","year":"2016"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2845997\/li_2026_oi_260029_1772216257.83842.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:30:23Z","timestamp":1772814623000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2845997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,2]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2026.0359","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]}}}