{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T16:56:47Z","timestamp":1793725007310,"version":"4.6.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T00:00:00Z","timestamp":1690502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Glob. Womens Health"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Postpartum hemorrhage (PPH) is a significant cause of maternal mortality worldwide, particularly in low- and middle-income countries. It is essential to develop effective prediction models to identify women at risk of PPH and implement appropriate interventions to reduce maternal morbidity and mortality. This study aims to predict the occurrence of postpartum hemorrhage using machine learning models based on antenatal, intrapartum, and postnatal visit data obtained from the Kenya Antenatal and Postnatal Care Research Collective cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>Four machine learning models \u2013 logistic regression, na\u00efve Bayes, decision tree, and random forest \u2013 were constructed using 67% training data (1,056\/1,576). The training data was further split into 67% for model building and 33% cross validation. Once the models are built, the remaining 33% (520\/1,576) independent test data was used for external validation to confirm the models' performance. Models were fine-tuned using feature selection through extra tree classifier technique. Model performance was assessed using accuracy, sensitivity, and area under the curve (AUC) of the receiver operating characteristics (ROC) curve.<\/jats:p><\/jats:sec><jats:sec><jats:title>Result<\/jats:title><jats:p>The na\u00efve Bayes model performed best with 0.95 accuracy, 0.97 specificity, and 0.76 AUC. Seven factors (anemia, limited prenatal care, hemoglobin concentrations, signs of pallor at intrapartum, intrapartum systolic blood pressure, intrapartum diastolic blood pressure, and intrapartum respiratory rate) were associated with PPH prediction in Kenyan population.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>This study demonstrates the potential of machine learning models in predicting PPH in the Kenyan population. Future studies with larger datasets and more PPH cases should be conducted to improve prediction performance of machine learning model. Such prediction algorithms would immensely help to construct a personalized obstetric path for each pregnant patient, improve resource allocation, and reduce maternal mortality and morbidity.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fgwh.2023.1161157","type":"journal-article","created":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T17:54:12Z","timestamp":1690566852000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Prediction of postpartum hemorrhage (PPH) using machine learning algorithms in a Kenyan population"],"prefix":"10.3389","volume":"4","author":[{"given":"Santosh Yogendra","family":"Shah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumant","family":"Saxena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satya Pavitra","family":"Rani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naresh","family":"Nelaturi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheena","family":"Gill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beth","family":"Tippett Barr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joyce","family":"Were","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sammy","family":"Khagayi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Ouma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor","family":"Akelo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Errol R.","family":"Norwitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dickens","family":"Onyango","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manoj","family":"Teltumbade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,7,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","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":"B2","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1016\/S0140-6736(06)69380-X","article-title":"Maternal mortality: who, when, where, and why","volume":"368","author":"Ronsmans","year":"2006","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1016\/S0140-6736(06)68397-9","article-title":"WHO Analysis of causes of maternal death: a systematic review","volume":"367","author":"Khan","year":"2006","journal-title":"Lancet"},{"key":"B4","year":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1016\/j.bpobgyn.2008.08.004","article-title":"Epidemiology of postpartum haemorrhage: a systematic review","volume":"22","author":"Carroli","year":"2008","journal-title":"Best Pract Res Clin Obstet Gynaecol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1177\/1745505717716860","article-title":"An update on the risk factors for and management of obstetric haemorrhage","volume":"13","author":"Sebghati","year":"2017","journal-title":"Womens Health (Lond)"},{"key":"B7","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1111\/j.1600-0412.2011.01119.x","article-title":"Long-term psychological impact of severe postpartum hemorrhage","volume":"90","author":"Sentilhes","year":"2011","journal-title":"Acta Obstet Gynecol Scand"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e80582","DOI":"10.1371\/journal.pone.0080582","article-title":"Reproductive health voucher program and facility based delivery in informal settlements in Nairobi: a longitudinal analysis","volume":"8","author":"Amendah","year":"2013","journal-title":"PLoS One"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12884-018-1708-2","article-title":"The effect of Kenya\u2019s free maternal health care policy on the utilization of health facility delivery services and maternal and neonatal mortality in public health facilities","volume":"18","author":"Gitobu","year":"2018","journal-title":"BMC Pregnancy Childbirth"},{"key":"B10","year":""},{"key":"B11","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1111\/1471-0528.16379","article-title":"Predicting risk of postpartum haemorrhage: a systematic review","volume":"128","author":"Neary","year":"2021","journal-title":"BJOG"},{"key":"B12","doi-asserted-by":"publisher","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":"B13","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1055\/s-0037-1606332","article-title":"Predicting postpartum hemorrhage (PPH) during cesarean delivery using the Leicester PPH predict tool: a retrospective cohort study","volume":"35","author":"Dunkerton","year":"2018","journal-title":"Am J Perinatol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/s00540-017-2365-8","article-title":"Development of a scoring system to predict massive postpartum transfusion in placenta previa totalis","volume":"31","author":"Kim","year":"2017","journal-title":"J Anesth"},{"key":"B15","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.ebiom.2019.11.010","article-title":"Radiomics analysis of placenta on T2WI facilitates prediction of postpartum haemorrhage: a multicentre study","volume":"50","author":"Wu","year":"2019","journal-title":"EBioMedicine"},{"key":"B16","author":"Wormer","year":""},{"key":"B17","doi-asserted-by":"publisher","first-page":"e168","DOI":"10.1097\/AOG.0000000000002351","article-title":"Practice bulletin No. 183: postpartum hemorrhage","volume":"130","year":"2017","journal-title":"Obstet Gynecol"},{"key":"B18","first-page":"e106","article-title":"Prevention and management of postpartum haemorrhage","volume":"124","author":"Mavrides","year":"2016","journal-title":"BJOG"},{"key":"B19","first-page":"5689","author":"Yoon","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1093\/jamia\/ocaa139","article-title":"Democratizing EHR analyses with FIDDLE: a flexible data-driven preprocessing pipeline for structured clinical data","volume":"27","author":"Tang","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"B21","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1093\/jamia\/ocab161","article-title":"Improving postpartum hemorrhage risk prediction using longitudinal electronic medical records","volume":"29","author":"Zheutlin","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1016\/S0895-4356(96)00002-9","article-title":"Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes","volume":"49","author":"Tu","year":"1996","journal-title":"J Clin Epidemiol"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"Hastie","year":"2009"},{"key":"B25","doi-asserted-by":"publisher","first-page":"100185","DOI":"10.1016\/j.xagr.2023.100185","article-title":"Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach","volume":"3","author":"Mehrnoush","year":"2023","journal-title":"AJOG Global Reports"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e34108","DOI":"10.2196\/34108","article-title":"Prediction of maternal hemorrhage using machine learning: retrospective cohort study","volume":"24","author":"Westcott","year":"2022","journal-title":"J Med Internet Res"},{"key":"B27","article-title":"On discriminative vs. Generative classifiers: a comparison of logistic regression and naive Bayes","author":"Ng","year":"2001"},{"key":"B28","first-page":"34","author":"Huang","year":"2011"},{"key":"B29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1002\/ijgo.14270","article-title":"A synthesis of clinical and health system bottlenecks to implementing new WHO postpartum hemorrhage recommendations: secondary data analysis of the Kenya confidential enquiry into maternal deaths 2014\u20132017","volume":"158","author":"Ameh","year":"2022","journal-title":"Int J Gynaecol Obstet"},{"key":"B30","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1093\/ejcts\/ezy180","article-title":"Statistical primer: developing and validating a risk prediction model","volume":"54","author":"Grant","year":"2018","journal-title":"Eur J Cardiothorac Surg"},{"key":"B31","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1136\/bmj.b606","article-title":"Prognosis and prognostic research: application and impact of prognostic models in clinical practice","volume":"338","author":"Moons","year":"2009","journal-title":"Br Med J"}],"container-title":["Frontiers in Global Women's Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgwh.2023.1161157\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T17:54:18Z","timestamp":1690566858000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgwh.2023.1161157\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,28]]},"references-count":31,"alternative-id":["10.3389\/fgwh.2023.1161157"],"URL":"https:\/\/doi.org\/10.3389\/fgwh.2023.1161157","relation":{},"ISSN":["2673-5059"],"issn-type":[{"value":"2673-5059","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,28]]},"article-number":"1161157"}}