{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:52:21Z","timestamp":1782921141240,"version":"3.54.5"},"reference-count":24,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100016989","name":"Korea University Medicine","doi-asserted-by":"publisher","award":["K1925051"],"award-info":[{"award-number":["K1925051"]}],"id":[{"id":"10.13039\/100016989","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Transfusion Medicine"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postpartum haemorrhage (PPH) accounts for approximately 27% of maternal deaths worldwide and often requires blood transfusion, along with its associated risks. In resource\u2010rich settings like South Korea, transfusion disparities persist, highlighting the need for predictive tools to optimise patient blood management (PBM).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To apply machine learning (ML) to rank predictors of transfusion in PPH using national claims data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This was a retrospective cohort study of 123\u2009763 women with PPH (2017\u20132019) from the National Health Insurance Service (NHIS) database (97% population coverage) in South Korea. The dependent variable was transfusion (yes\/no). We used 48 independent variables (demographics, obstetric status, medications and comorbidities) derived from ICD\u201010\/ATC codes. The random forest model (100 trees, Gini standard impurity criterion) was trained with 80% of the data and validated with 20% of the data after random split (area under the receiver operating characteristic curve [AUC] is a model performance metric). Permutation importance rankings were used for predictors; Shapley Additive Explanation (SHAP) values assessed directional associations and interactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The transfusion rate was 6.7% (8308\/123\u2009763). The model achieved an AUC of 77.0% (95% confidence interval: 76.9\u201377.2). The top 10 predictors by variable importance were coagulopathy (0.311), placenta accreta (0.146), placenta previa (0.129), caesarean section (0.048), uterine atony (0.045), preterm delivery (0.041), age (0.037), vaginal laceration (0.029), iron use (0.025) and socioeconomic status (0.020). SHAP analysis confirmed a positive effect (e.g., maximum SHAP for placenta accreta\u2009=\u20090.2582), and the synergistic interaction between placenta accreta and coagulopathy amplified the risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Coagulopathy and placental abnormalities are the most important drivers of transfusion in PPH. Explanatory ML enhances risk stratification beyond traditional models, informing PBM protocols to curb abuse and inequity. Potential integration into NHIS systems could protect maternal outcomes globally.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/tme.70097","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:29:03Z","timestamp":1782919743000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prioritising parameters to minimise blood transfusions for postpartum haemorrhage: A machine learning study using national population data"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6314-4621","authenticated-orcid":false,"given":"Ki Hoon","family":"Ahn","sequence":"first","affiliation":[{"name":"Department of Obstetrics and Gynecology Korea University College of Medicine, Korea University Anam Hospital  Seoul Korea"},{"name":"Bloodless Medicine Center Korea University Anam Hospital  Seoul Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu\u2010Min","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology Korea University College of Medicine, Korea University Anam Hospital  Seoul Korea"},{"name":"School of Mechanical Engineering Korea University College of Engineering  Seoul Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwang\u2010Sig","family":"Lee","sequence":"additional","affiliation":[{"name":"Bloodless Medicine Center Korea University Anam Hospital  Seoul Korea"},{"name":"AI Center, Korea University College of Medicine Korea University Anam Hospital  Seoul Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"issue":"1","key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/ijgo.12096","article-title":"A systematic review of maternal near miss and mortality due to postpartum hemorrhage","volume":"137","author":"Maswime S","year":"2017","journal-title":"Int J Gynaecol Obstet"},{"key":"e_1_2_10_3_1","volume-title":"A roadmap to combat postpartum haemorrhage between 2023 and 2030","author":"World Health Organization","year":"2023"},{"issue":"7","key":"e_1_2_10_4_1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0041114","article-title":"Identifying regional variation in the prevalence of postpartum haemorrhage: a systematic review and meta\u2010analysis","volume":"7","author":"Calvert C","year":"2012","journal-title":"PLoS One"},{"issue":"4","key":"e_1_2_10_5_1","doi-asserted-by":"crossref","first-page":"e626","DOI":"10.1016\/S2214-109X(24)00560-6","article-title":"Global and regional causes of maternal deaths 2009\u201320: a WHO systematic analysis","volume":"13","author":"Cresswell JA","year":"2025","journal-title":"Lancet Glob Health"},{"key":"e_1_2_10_6_1","first-page":"6","article-title":"Blood transfusion in obstetrics","volume":"5","author":"Green\u2010top Guideline No 47","year":"2015","journal-title":"Obstet Gynecol"},{"key":"e_1_2_10_7_1","volume-title":"StatPearls","author":"Killeen RB","year":"2025"},{"issue":"17","key":"e_1_2_10_8_1","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1056\/NEJMra1513247","article-title":"Postpartum hemorrhage","volume":"384","author":"Bienstock JL","year":"2021","journal-title":"N Engl J Med"},{"issue":"1","key":"e_1_2_10_9_1","doi-asserted-by":"crossref","DOI":"10.1186\/s12884-017-1384-7","article-title":"Incidence, management and outcome of women requiring massive transfusion after childbirth in The Netherlands: secondary analysis of a nationwide cohort study between 2004 and 2006","volume":"17","author":"Ramler PI","year":"2017","journal-title":"BMC Pregnancy Childbirth"},{"issue":"6","key":"e_1_2_10_10_1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0233274","article-title":"Risk factors for blood transfusion in traumatic and postpartum hemorrhage patients: analysis of the CRASH\u20102 and WOMAN trials","volume":"15","author":"Kolin DA","year":"2020","journal-title":"PLoS One"},{"issue":"6","key":"e_1_2_10_11_1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0274041","article-title":"Primary postpartum haemorrhage and longer\u2010term physical, psychological, and psychosocial health outcomes for women and their partners in high income countries: a mixed\u2010methods systematic review","volume":"18","author":"Latt SM","year":"2023","journal-title":"PLoS One"},{"issue":"1","key":"e_1_2_10_12_1","first-page":"5","article-title":"Patient blood management: commentary: patient blood management \u2013 what is it as a concept?","volume":"23","author":"Ozawa\u2010Morriello J","year":"2025","journal-title":"Blood Transfus"},{"issue":"19","key":"e_1_2_10_13_1","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1001\/jama.2016.9185","article-title":"Clinical practice guidelines from the AABB: red blood cell transfusion thresholds and storage","volume":"316","author":"Carson JL","year":"2016","journal-title":"Jama"},{"issue":"6","key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.5468\/ogs.22288","article-title":"Patient blood management to minimize transfusions during the postpartum period","volume":"66","author":"Song KH","year":"2023","journal-title":"Obstet Gynecol Sci"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.bpobgyn.2019.04.005","article-title":"Tranexamic acid for post\u2010partum haemorrhage: what, who and when","volume":"61","author":"Brenner A","year":"2019","journal-title":"Best Pract Res Clin Obstet Gynaecol"},{"issue":"1","key":"e_1_2_10_16_1","doi-asserted-by":"crossref","DOI":"10.1186\/s40064-016-2620-8","article-title":"The income\u2010based disparities in preeclampsia and postpartum hemorrhage: a study of the Korean National Health Insurance cohort data from 2002 to 2013","volume":"5","author":"Choe SA","year":"2016","journal-title":"Springerplus"},{"issue":"2","key":"e_1_2_10_17_1","doi-asserted-by":"crossref","first-page":"113","DOI":"10.5468\/ogs.21234","article-title":"Artificial intelligence in obstetrics","volume":"65","author":"Ahn KH","year":"2022","journal-title":"Obstet Gynecol Sci"},{"issue":"7","key":"e_1_2_10_18_1","doi-asserted-by":"crossref","DOI":"10.2196\/34108","article-title":"Prediction of maternal hemorrhage using machine learning: retrospective cohort study","volume":"24","author":"Westcott JM","year":"2022","journal-title":"J Med Internet Res"},{"key":"e_1_2_10_19_1","unstructured":"KumarA HoraH RohillaA KumarP.Explainable Artificial Intelligence (XAI) for healthcare: enhancing transparency. Paper presented at:Proceedings of Fifth International Conference on Computing Communications and Cyber\u2010Security: IC4S'05 Vol. 22024."},{"key":"e_1_2_10_20_1","volume-title":"WHO Recommendations for the Prevention and Treatment of Postpartum Haemorrhage","author":"WHO guidelines approved by the guidelines review committee","year":"2012"},{"issue":"4","key":"e_1_2_10_21_1","doi-asserted-by":"crossref","first-page":"e168","DOI":"10.1097\/AOG.0000000000002351","article-title":"Practice bulletin no. 183: postpartum hemorrhage","volume":"130","year":"2017","journal-title":"Obstet Gynecol"},{"issue":"10084","key":"e_1_2_10_22_1","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.1016\/S0140-6736(17)30638-4","article-title":"Effect of early tranexamic acid administration on mortality, hysterectomy, and other morbidities in women with post\u2010partum haemorrhage (WOMAN): an international, randomised, double\u2010blind, placebo\u2010controlled trial","volume":"389","author":"Shakur H","year":"2017","journal-title":"Lancet"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2393-9-55","article-title":"Trends in postpartum hemorrhage in high resource countries: a review and recommendations from the International Postpartum Hemorrhage Collaborative Group","volume":"9","author":"Knight M","year":"2009","journal-title":"BMC Pregnancy Childbirth"},{"issue":"12","key":"e_1_2_10_24_1","article-title":"Transfusion thresholds for guiding red blood cell transfusion","volume":"12","author":"Carson JL","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"issue":"2","key":"e_1_2_10_25_1","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/j.1751-2824.2009.01251.x","article-title":"Patient blood management \u2013 a new paradigm for transfusion medicine?","volume":"4","author":"Thomson A","year":"2009","journal-title":"ISBT Sci Ser"}],"container-title":["Transfusion Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tme.70097","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/tme.70097","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tme.70097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:29:14Z","timestamp":1782919754000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/tme.70097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":24,"alternative-id":["10.1111\/tme.70097"],"URL":"https:\/\/doi.org\/10.1111\/tme.70097","archive":["Portico"],"relation":{},"ISSN":["0958-7578","1365-3148"],"issn-type":[{"value":"0958-7578","type":"print"},{"value":"1365-3148","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"assertion":[{"value":"2025-11-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"tme.70097"}}