{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T18:26:57Z","timestamp":1795026417902,"version":"4.10.2"},"reference-count":47,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"4","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,4]]},"abstract":"<jats:sec>\n                    <jats:title>OBJECTIVE:<\/jats:title>\n                    <jats:p>To predict a woman's risk of postpartum hemorrhage at labor admission using machine learning and statistical models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS:<\/jats:title>\n                    <jats:p>Predictive models were constructed and compared using data from 10 of 12 sites in the U.S. Consortium for Safe Labor Study (2002\u20132008) that consistently reported estimated blood loss at delivery. The outcome was postpartum hemorrhage, defined as an estimated blood loss at least 1,000 mL. Fifty-five candidate risk factors routinely available on labor admission were considered. We used logistic regression with and without lasso regularization (lasso regression) as the two statistical models, and random forest and extreme gradient boosting as the two machine learning models to predict postpartum hemorrhage. Model performance was measured by C statistics (ie, concordance index), calibration, and decision curves. Models were constructed from the first phase (2002\u20132006) and externally validated (ie, temporally) in the second phase (2007\u20132008). Further validation was performed combining both temporal and site-specific validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS:<\/jats:title>\n                    <jats:p>Of the 152,279 assessed births, 7,279 (4.8%, 95% CI 4.7\u20134.9) had postpartum hemorrhage. All models had good-to-excellent discrimination. The extreme gradient boosting model had the best discriminative ability to predict postpartum hemorrhage (C statistic: 0.93; 95% CI 0.92\u20130.93), followed by random forest (C statistic: 0.92; 95% CI 0.91\u20130.92). The lasso regression model (C statistic: 0.87; 95% CI 0.86\u20130.88) and logistic regression (C statistic: 0.87; 95% CI 0.86\u20130.87) had lower-but-good discriminative ability. The above results held with validation across both time and sites. Decision curve analysis demonstrated that, although all models provided superior net benefit when clinical decision thresholds were between 0% and 80% predicted risk, the extreme gradient boosting model provided the greatest net benefit.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION:<\/jats:title>\n                    <jats:p>Postpartum hemorrhage on labor admission can be predicted with excellent discriminative ability using machine learning and statistical models. Further clinical application is needed, which may assist health care providers to be prepared and triage at-risk women.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/aog.0000000000003759","type":"journal-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T12:29:27Z","timestamp":1584102567000},"page":"935-944","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":175,"title":["Machine Learning and Statistical Models to Predict Postpartum Hemorrhage"],"prefix":"10.1097","volume":"135","author":[{"given":"Kartik K.","family":"Venkatesh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert A.","family":"Strauss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chad A.","family":"Grotegut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Philip","family":"Heine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nancy C.","family":"Chescheir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey S. A.","family":"Stringer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David M.","family":"Stamilio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine M.","family":"Menard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. Eric","family":"Jelovsek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20261118","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.1016\/S2214-109X(14)70227-X","article-title":"Global causes of maternal death: a WHO systematic analysis","volume":"2","author":"Say","year":"2014","journal-title":"Lancet Glob Health"},{"key":"R2-20261118","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1213\/ANE.0b013e3181d74898","article-title":"The epidemiology of postpartum hemorrhage in a large, nationwide sample of deliveries","volume":"110","author":"Bateman","year":"2010","journal-title":"Anaesth Analgesia"},{"key":"R3-20261118","doi-asserted-by":"crossref","first-page":"353.e1","DOI":"10.1016\/j.ajog.2010.01.011","article-title":"Trends in postpartum hemorrhage: United States, 1994-2006","volume":"202","author":"Callaghan","year":"2010","journal-title":"Am J Obstet Gynecol"},{"key":"R4-20261118","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1089\/jwh.2013.4617","article-title":"Maternal mortality and morbidity in the United States: where are we now?","volume":"23","author":"Creanga","year":"2014","journal-title":"J Womens Health"},{"key":"R5-20261118","doi-asserted-by":"crossref","first-page":"133.e1","DOI":"10.1016\/j.ajog.2007.12.020","article-title":"Identification of severe maternal morbidity during delivery hospitalizations, United States, 1991-2003","volume":"199","author":"Callaghan","year":"2008","journal-title":"Am J Obstet Gynecol"},{"key":"R6-20261118","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1055\/s-0037-1606275","article-title":"Implementation of quantification of blood loss does not improve prediction of hemoglobin drop in deliveries with average blood loss","volume":"35","author":"Hamm","year":"2018","journal-title":"Am J Perinatol"},{"key":"R7-20261118","doi-asserted-by":"crossref","first-page":"e168","DOI":"10.1097\/AOG.0000000000002351","article-title":"Postpartum hemorrhage","volume":"130","year":"2017","journal-title":"Obstet Gynecol"},{"key":"R9-20261118","doi-asserted-by":"crossref","first-page":"76.e1","DOI":"10.1016\/j.ajog.2015.02.023","article-title":"Prevention and management of postpartum hemorrhage: a comparison of 4 national guidelines","volume":"213","author":"Dahlke","year":"2015","journal-title":"Am J Obstet Gynecol"},{"key":"R10-20261118","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.ajog.2014.07.012","article-title":"Comprehensive maternal hemorrhage protocols reduce the use of blood products and improve patient safety","volume":"212","author":"Shields","year":"2015","journal-title":"Am J Obstet Gynecol"},{"key":"R11-20261118","first-page":"155","article-title":"National partnership for maternal safety; council on patient safety in women's health care. National partnership for maternal safety: consensus bundle on obstetric hemorrhage","volume":"126","author":"Main","year":"2015","journal-title":"Obstetrics Gynecol"},{"key":"R12-20261118","doi-asserted-by":"crossref","first-page":"51.e1","DOI":"10.1016\/j.ajog.2013.03.011","article-title":"Risk factors for uterine atony\/postpartum hemorrhage requiring treatment after vaginal delivery","volume":"209","author":"Wetta","year":"2013","journal-title":"Am J Obstetrics Gynecol"},{"key":"R13-20261118","doi-asserted-by":"crossref","first-page":"449.e1","DOI":"10.1016\/j.ajog.2013.07.007","article-title":"Incidence, risk factors, and temporal trends in severe postpartum hemorrhage","volume":"209","author":"Kramer","year":"2013","journal-title":"Am J Obstet Gynecol"},{"key":"R14-20261118","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1186\/1471-2393-11-97","article-title":"Inability to predict postpartum hemorrhage: insights from Egyptian intervention data","volume":"11","author":"Prata","year":"2011","journal-title":"BMC Pregnancy Childbirth"},{"key":"R15-20261118","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1080\/00016340802087660","article-title":"Risk factors and interventions associated with major primary postpartum hemorrhage unresponsive to first-line conventional therapy","volume":"87","author":"Mousa","year":"2008","journal-title":"Acta Obstet Gynecol Scand"},{"key":"R16-20261118","doi-asserted-by":"crossref","first-page":"e1","DOI":"10.1016\/j.thromres.2011.09.010","article-title":"Risk factors for postpartum hemorrhage in a cohort of 6011 Italian women","volume":"129","author":"Biguzzi","year":"2012","journal-title":"Thromb Res"},{"key":"R17-20261118","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1007\/s00404-015-3725-y","article-title":"Revisit of risk factors for major obstetric hemorrhage: insights from a large medical center","volume":"292","author":"Helman","year":"2015","journal-title":"Arch Obstet Gynecol"},{"key":"R18-20261118","first-page":"601","article-title":"Current applications of big data and machine learning in cardiology","volume":"16","author":"Cuocolo","year":"2019","journal-title":"J Geriatr Cardiol"},{"key":"R19-20261118","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1001\/jama.2019.10306","article-title":"Making machine learning models clinically useful","volume":"322","author":"Shah","year":"2019","journal-title":"J Am Med Assoc"},{"key":"R20-20261118","doi-asserted-by":"crossref","first-page":"e186937","DOI":"10.1001\/jamanetworkopen.2018.6937","article-title":"Machine learning-based prediction of clinical outcomes for children during emergency department triage","volume":"2","author":"Goto","year":"2019","journal-title":"JAMA Open Netw"},{"key":"R21-20261118","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/j.ajog.2019.01.208","article-title":"Automated early detection of obstetric complications: theoretic and methodologic considerations","volume":"220","author":"Escobar","year":"2019","journal-title":"Am J Obstet Gynecol"},{"key":"R22-20261118","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1093\/jamia\/ocz106","article-title":"Assessing clinical heterogeneity in sepsis through treatment patterns and machine learning","volume":"26","author":"Fohner","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"R23-20261118","doi-asserted-by":"crossref","first-page":"326.e1","DOI":"10.1016\/j.ajog.2010.06.058","article-title":"Contemporary cesarean delivery practice in the United States","volume":"203","author":"Zhang","year":"2010","journal-title":"Am J Obstet Gynecol"},{"key":"R24-20261118","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M14-0698","article-title":"Transparent reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration","volume":"162","author":"Moons","year":"2015","journal-title":"Ann Intern Med"},{"key":"R25-20261118","doi-asserted-by":"crossref","first-page":"6102","DOI":"10.1016\/j.vaccine.2016.03.039","article-title":"Postpartum haemorrhage: case definition and guidelines for data collection, analysis, and presentation of immunization safety data","volume":"34","author":"Kerr","year":"2016","journal-title":"Vaccine"},{"key":"R28-20261118","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1097\/AOG.0000000000000322","article-title":"Executive summary of the reVITALize initiative: standardizing obstetric data definitions","volume":"124","author":"Menard","year":"2014","journal-title":"Obstetrics Gynecol"},{"key":"R29-20261118","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc"},{"key":"R30-20261118","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learn"},{"key":"R32-20261118","doi-asserted-by":"crossref","DOI":"10.1093\/aje\/kwz189","article-title":"What is machine learning? A primer for the epidemiologist","author":"Bi","year":"2019","journal-title":"Am J Epidemiol"},{"key":"R33-20261118","doi-asserted-by":"crossref","first-page":"1806","DOI":"10.1001\/jama.2019.16489","article-title":"How to read articles that use machine learning users' guides to the medical literature","volume":"322","author":"Liu","year":"2019","journal-title":"J Am Med Assoc"},{"key":"R34-20261118","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1097\/AOG.0000000000001269","article-title":"Predicting risk of urinary incontinence and adverse events after midurethral sling surgery in women","volume":"127","author":"Jelovsek","year":"2016","journal-title":"Obstetrics Gynecol"},{"key":"R35-20261118","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":"Vickers","year":"2006","journal-title":"Med Decis Making"},{"key":"R36-20261118","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1001\/jama.2015.37","article-title":"Decision curve analysis","volume":"313","author":"Fitzgerald","year":"2015","journal-title":"J Am Med Assoc"},{"key":"R37-20261118","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1002\/sim.4067","article-title":"Multiple imputation using chained equations: issues and guidance for practice","volume":"30","author":"White","year":"2011","journal-title":"Stat Med"},{"key":"R38-20261118","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1111\/ecog.02881","article-title":"Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure","volume":"40","author":"Roberts","year":"2017","journal-title":"Ecography"},{"key":"R40-20261118","doi-asserted-by":"crossref","first-page":"e41","DOI":"10.1097\/AOG.0000000000003383","article-title":"Levels of maternal care","volume":"134","year":"2019","journal-title":"Obstet Gynecol"},{"key":"R41-20261118","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1097\/AOG.0b013e3182941c78","article-title":"Clinical validation of risk stratification criteria for peripartum hemorrhage","volume":"122","author":"Dilla","year":"2013","journal-title":"Obstetrics Gynecol"},{"key":"R42-20261118","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1111\/1471-0528.15607","article-title":"Predicting common maternal postpartum complications: leveraging health administrative data and machine learning","volume":"126","author":"Betts","year":"2019","journal-title":"BJOG"},{"key":"R43-20261118","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1111\/aogs.12352","article-title":"Prediction of postpartum hemorrhage in women with gestational hypertension or mild preeclampsia at term","volume":"93","author":"Koopmans","year":"2014","journal-title":"Acta Obstet Gynecol Scand"},{"key":"R44-20261118","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1055\/s-0039-1678604","article-title":"A regression model for prediction of cesarean-associated blood transfusion","volume":"36","author":"Albright","year":"2019","journal-title":"Am J Perinatol"},{"key":"R45-20261118","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1097\/AOG.0000000000003319","article-title":"Predictive model of factors associated with maternal intensive care unit admission","volume":"134","author":"Rossi","year":"2019","journal-title":"Obstetrics Gynecol"},{"key":"R46-20261118","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1097\/AOG.0000000000003377","article-title":"Predictive model for failed induction of labor among obese women","volume":"134","author":"Rossi","year":"2019","journal-title":"Obstetrics Gynecol"},{"key":"R47-20261118","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1080\/14767058.2017.1306050","article-title":"Risk for postpartum hemorrhage, transfusion, and hemorrhage-related morbidity at low, moderate, and high volume hospitals","volume":"31","author":"Merriam","year":"2018","journal-title":"J Matern Fetal Neonatal Med"},{"key":"R49-20261118","doi-asserted-by":"crossref","first-page":"298.e1","DOI":"10.1016\/j.ajog.2017.01.017","article-title":"Reduction of severe maternal morbidity from hemorrhage using a state perinatal quality collaborative","volume":"216","author":"Main","year":"2017","journal-title":"Am J Obstet Gynecol"},{"key":"R50-20261118","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1097\/AOG.0000000000003574","article-title":"Evaluation of risk-assessment tools for severe postpartum hemorrhage in women undergoing cesarean delivery","volume":"134","author":"Kawakita","year":"2019","journal-title":"Obstetrics Gynecol"},{"key":"R51-20261118","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1001\/jama.2019.4914","article-title":"Artificial intelligence in health care: will the value match the hype?","volume":"321","author":"Emanuel","year":"2019","journal-title":"J Am Med Assoc"},{"key":"R52-20261118","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1097\/01.AOG.0000137873.07820.34","article-title":"Estimating blood loss: can teaching significantly improve visual estimation?","volume":"104","author":"Dildy","year":"2004","journal-title":"Obstetrics Gynecol"},{"key":"R53-20261118","doi-asserted-by":"crossref","first-page":"e57594","DOI":"10.1371\/journal.pone.0057594","article-title":"A systematic review of the relationship between blood loss and clinical signs","volume":"8","author":"Pacagnella","year":"2013","journal-title":"PLoS One"}],"container-title":["Obstetrics &amp; Gynecology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/AOG.0000000000003759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T18:03:19Z","timestamp":1795024999000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/AOG.0000000000003759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1097\/aog.0000000000003759","relation":{},"ISSN":["0029-7844","1873-233X"],"issn-type":[{"value":"0029-7844","type":"print"},{"value":"1873-233X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]},"assertion":[{"value":"2019-11-20","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-01-16","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}