Integrating Bleeding Velocity and Clinical Indicators into Machine Learning Models for Predicting Postpartum Hemorrhage: Development and External Validation Study

Integrating Bleeding Velocity and Clinical Indicators into Machine Learning Models for Predicting Postpartum Hemorrhage: Development and External Validation Study | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 10 December 2025 V1 Latest version Share on Integrating Bleeding Velocity and Clinical Indicators into Machine Learning Models for Predicting Postpartum Hemorrhage: Development and External Validation Study Authors : Oluwafunmilola Deborah Awe 0000-0002-6495-2030 , Cristiano Torezzan , Anderson Pinheiro , Sirlei Siani , Jill Durocher , and Rodolfo Pacagnella 0000-0002-5739-0009 [email protected] Authors Info & Affiliations https://doi.org/10.22541/au.176540414.43901598/v1 264 views 115 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Objective To develop and externally validate predictive models for early detection of postpartum hemorrhage by combining clinical, hemodynamic, and temporal blood loss indicators. Design Multicenter retrospective model development and external validation study. Setting A Brazilian tertiary referral hospital and pooled clinical trial and observational datasets from low- and middle-income countries. Population or Sample Model training used data from a Brazilian tertiary hospital cohort (n = 270) and external validation employed pooled datasets from randomized and observational studies (n = 2,379). Methods Predictive models were developed using maternal demographics, delivery characteristics, pre-delivery hemoglobin, blood loss at 30 minutes postpartum, and bleeding velocity. Statistical and machine learning approaches including logistic regression, random forest, and XGBoost were evaluated. Model discrimination and performance were assessed using area under the receiver operating characteristic curve (AUC), F1-score, sensitivity, and additional validation metrics. Main Outcome Measures Binary; occurrence of postpartum hemorrhage defined as blood loss ≥500 mL (yes/no), along with model discrimination, calibration, and clinical predictive performance. Results Early bleeding velocity and blood loss at 30 minutes were the strongest predictors of PPH. Generalized linear models achieved high discrimination (internal AUC ~ 0.98) and strong agreement. Machine learning models performed well but did not consistently outperform logistic regression. In external validation, simpler regression-based models demonstrated equal or superior discrimination (AUCs up to 0.996) and more stable calibration. Reduced predictor models retained good performance (external AUC ~0.89–0.94), while expanded models maintained robust performance (AUC ~0.92–0.98). Conclusions Integration of early hemodynamic and temporal bleeding measurements could substantially improve early prediction of postpartum hemorrhage. These findings support scalable, data-driven tools for timely intervention and reduction of maternal morbidity. Supplementary Material File (bjog_incorporating early bleeding dynamics into machine learning_rcp_funmi_review.docx) Download 1017.66 KB File (table 1-maternal and clinical characteristics.docx) Download 14.85 KB File (table 2_xtic_ext.docx) Download 15.32 KB Information & Authors Information Version history V1 Version 1 10 December 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords maternal medicine obstetric haemorrhage puerperium Authors Affiliations Oluwafunmilola Deborah Awe 0000-0002-6495-2030 Universidade Estadual de Campinas Faculdade de Ciencias Medicas View all articles by this author Cristiano Torezzan Universidade Estadual de Campinas Faculdade de Ciencias Aplicadas View all articles by this author Anderson Pinheiro Universidade Estadual de Campinas Faculdade de Ciencias Medicas View all articles by this author Sirlei Siani Universidade Estadual de Campinas Faculdade de Ciencias Medicas View all articles by this author Jill Durocher Gynuity Health Projects View all articles by this author Rodolfo Pacagnella 0000-0002-5739-0009 [email protected] Universidade Estadual de Campinas Faculdade de Ciencias Medicas View all articles by this author Metrics & Citations Metrics Article Usage 264 views 115 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Oluwafunmilola Deborah Awe, Cristiano Torezzan, Anderson Pinheiro, et al. Integrating Bleeding Velocity and Clinical Indicators into Machine Learning Models for Predicting Postpartum Hemorrhage: Development and External Validation Study. Authorea . 10 December 2025. DOI: https://doi.org/10.22541/au.176540414.43901598/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176540414.43901598/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9ffbd1b12b7c300f',t:'MTc3OTQ1Mjg4OQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();