{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:52:12Z","timestamp":1791359532785,"version":"4.3.1"},"reference-count":34,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81872286"],"award-info":[{"award-number":["81872286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82073241"],"award-info":[{"award-number":["82073241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["7254324"],"award-info":[{"award-number":["7254324"]}],"id":[{"id":"10.13039\/501100005089","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>Subjective, inconsistent clinician judgement on red blood cell (RBC) transfusion demand causes unnecessary blood wastage, increased perioperative safety risks, and poorly balanced hospital blood inventory. To tackle these persistent clinical limitations, we developed a workflow\u2010adapted clinical decision support tool: a one\u2010dimensional convolutional neural network (1D CNN) trained on routinely acquired haematological and clinical variables to stratify inpatient RBC transfusion volume categories.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using a retrospective cohort of 7,250 patients from Beijing Friendship Hospital (April 2024\u2013June 2025), we trained a 1D CNN on 19 standardised pre\u2010transfusion variables to predict transfusion volume categories (1, 2, 3, 4, \u22655\u2009units). The model was optimised with Adam and evaluated on a 30% hold\u2010out test set. Comprehensive characterisation of the cohort's baseline clinical features was also performed to clearly define the transfusion contexts and clinical indications of the study population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the 30% hold\u2010out test set, the 1D CNN reached an overall accuracy of 0.7314 and converged without overfitting. The model accurately identified the predominant 2\u2009units transfusion class (68.03% of cases, precision 0.7314). However, performance was limited in minority classes (\u22655\u2009units and 3\u2009units), which showed low prevalence (&lt;\u20095%) and overlapping haemoglobin values (60\u201380\u2009g\/L), indicating a critical safety limitation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The 1D CNN reliably forecasts routine transfusion requirements in a single\u2010center setting but under\u2010detects high\u2010volume transfusion events. External validation across diverse clinical centers, targeted data enrichment for minority classes, and development of indication\u2010specific sub\u2010models are mandatory to improve the model's generalizability and clinical utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/tme.70126","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:15:38Z","timestamp":1791357338000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Convolutional neural network for red blood cell transfusion prediction: A machine learning based study"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0955-030X","authenticated-orcid":false,"given":"Liyun","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Blood Transfusion Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Medical Digital Intelligence Innovation Center Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9498-1783","authenticated-orcid":false,"given":"Mengyun","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6637-0002","authenticated-orcid":false,"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Wang","sequence":"additional","affiliation":[{"name":"Medical Digital Intelligence Innovation Center Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9777-3242","authenticated-orcid":false,"given":"Xiaofei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion Beijing Friendship Hospital, Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"issue":"10","key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"2859","DOI":"10.3390\/jcm11102859","article-title":"Blood transfusion reactions\u2010a comprehensive review of the literature including a swiss perspective","volume":"11","author":"Ackfeld T","year":"2022","journal-title":"J Clin Med"},{"issue":"1","key":"e_1_2_10_3_1","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1111\/anae.12893","article-title":"Evidence and triggers for the transfusion of blood and blood products","volume":"70","author":"Shah A","year":"2015","journal-title":"Anaesthesia"},{"issue":"6","key":"e_1_2_10_4_1","first-page":"459","article-title":"Patient blood management: transfusion appropriateness in the post\u2010operative period","volume":"17","author":"Di Bartolomeo E","year":"2019","journal-title":"Blood Transfus"},{"issue":"12","key":"e_1_2_10_5_1","first-page":"Cd002042","article-title":"Transfusion thresholds for guiding red blood cell transfusion","volume":"12","author":"Carson JL","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","DOI":"10.3389\/fimmu.2023.1175387","article-title":"Update on transfusion\u2010related acute lung injury: an overview of its pathogenesis and management","volume":"14","author":"Yu Y","year":"2023","journal-title":"Front Immunol"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.blre.2021.100891","article-title":"The recipe for TACO: a narrative review on the pathophysiology and potential mitigation strategies of transfusion\u2010associated circulatory overload","volume":"52","author":"Bulle EB","year":"2022","journal-title":"Blood Rev"},{"issue":"17","key":"e_1_2_10_8_1","doi-asserted-by":"crossref","first-page":"1831","DOI":"10.1182\/blood-2018-10-833988","article-title":"Noninfectious transfusion\u2010associated adverse events and their mitigation strategies","volume":"133","author":"Goel R","year":"2019","journal-title":"Blood"},{"issue":"3","key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1213\/ANE.0000000000005873","article-title":"A global definition of patient blood management","volume":"135","author":"Shander A","year":"2022","journal-title":"Anesth Analg"},{"issue":"7","key":"e_1_2_10_10_1","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1111\/anae.16579","article-title":"Provision of peri\u2010operative patient blood management strategies in the UK: a national survey of practice","volume":"80","author":"Warnakulasuriya SR","year":"2025","journal-title":"Anaesthesia"},{"issue":"1","key":"e_1_2_10_11_1","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1111\/bjh.14641","article-title":"Impact of red blood cell transfusion strategies in haemato\u2010oncological patients: a systematic review and meta\u2010analysis","volume":"178","author":"Hoeks MPA","year":"2017","journal-title":"Br J Haematol"},{"issue":"11","key":"e_1_2_10_12_1","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1111\/pan.14736","article-title":"Development and validation of a multivariable prediction model in pediatric liver transplant patients for predicting intensive care unit length of stay","volume":"33","author":"Siddiqui A","year":"2023","journal-title":"Paediatr Anaesth"},{"issue":"1","key":"e_1_2_10_13_1","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1186\/s12871-024-02832-y","article-title":"An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery","volume":"24","author":"Zhou Y","year":"2024","journal-title":"BMC Anesthesiol"},{"issue":"13","key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine, 2023","volume":"388","author":"Haug CJ","year":"2023","journal-title":"N Engl J Med"},{"issue":"3","key":"e_1_2_10_15_1","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1213\/ANE.0000000000006047","article-title":"Artificial intelligence and machine learning in patient blood management: a scoping review","volume":"135","author":"Meier JM","year":"2022","journal-title":"Anesth Analg"},{"issue":"20","key":"e_1_2_10_16_1","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo RC","year":"2015","journal-title":"Circulation"},{"issue":"3","key":"e_1_2_10_17_1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaa185","article-title":"TERL: classification of transposable elements by convolutional neural networks","volume":"22","author":"Cruz MHP","year":"2021","journal-title":"Brief Bioinform"},{"issue":"5","key":"e_1_2_10_18_1","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"Min S","year":"2017","journal-title":"Brief Bioinform"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.ymeth.2019.04.008","article-title":"Deep learning in bioinformatics: introduction, application, and perspective in the big data era","volume":"166","author":"Li Y","year":"2019","journal-title":"Methods"},{"issue":"4","key":"e_1_2_10_20_1","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1517\/17460441.2012.668182","article-title":"Decision tree models for data mining in hit discovery","volume":"7","author":"Hammann F","year":"2012","journal-title":"Expert Opin Drug Discovery"},{"issue":"5","key":"e_1_2_10_21_1","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1023\/A:1016409317640","article-title":"Decision trees: an overview and their use in medicine","volume":"26","author":"Podgorelec V","year":"2002","journal-title":"J Med Syst"},{"issue":"6","key":"e_1_2_10_22_1","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1016\/j.ajodo.2023.09.011","article-title":"Decision trees and random forests","volume":"164","author":"Becker T","year":"2023","journal-title":"Am J Orthod Dentofacial Orthop"},{"issue":"2","key":"e_1_2_10_23_1","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad002","article-title":"A review on longitudinal data analysis with random forest","volume":"24","author":"Hu J","year":"2023","journal-title":"Brief Bioinform"},{"issue":"5","key":"e_1_2_10_24_1","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.ajodo.2023.08.003","article-title":"Support vector machines","volume":"164","author":"Valkenborg D","year":"2023","journal-title":"Am J Orthod Dentofacial Orthop"},{"issue":"11","key":"e_1_2_10_25_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2024.111106","article-title":"Development and validation of machine learning models for intraoperative blood transfusion prediction in severe lumbar disc herniation","volume":"27","author":"Liu Q","year":"2024","journal-title":"iScience"},{"issue":"9","key":"e_1_2_10_26_1","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1097\/EJA.0000000000001721","article-title":"Machine learning\u2010based prediction of massive perioperative allogeneic blood transfusion in cardiac surgery","volume":"39","author":"Tschoellitsch T","year":"2022","journal-title":"Eur J Anaesthesiol"},{"issue":"3","key":"e_1_2_10_27_1","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1007\/s10877-023-01112-3","article-title":"A precise blood transfusion evaluation model for aortic surgery: a single\u2010center retrospective study","volume":"38","author":"Che J","year":"2024","journal-title":"J Clin Monit Comput"},{"issue":"1","key":"e_1_2_10_28_1","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1186\/s12911-023-02286-1","article-title":"Construction and effect evaluation of prediction model for red blood cell transfusion requirement in cesarean section based on artificial intelligence","volume":"23","author":"Chen H","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"e_1_2_10_29_1","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1097\/ANA.0000000000000793","article-title":"Development and performance evaluation of a clinical predictive model to estimate the risk of red blood cell requirements in brain tumor surgery","volume":"35","author":"Tom\u00e1s\u2010Biosca A","year":"2023","journal-title":"J Neurosurg Anesthesiol"},{"issue":"1","key":"e_1_2_10_30_1","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: a large\u2010scale benchmark experiment","volume":"19","author":"Couronn\u00e9 R","year":"2018","journal-title":"BMC Bioinformatics"},{"issue":"13","key":"e_1_2_10_31_1","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1056\/NEJMp1606181","article-title":"Predicting the future \u2010 big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer Z","year":"2016","journal-title":"N Engl J Med"},{"issue":"1","key":"e_1_2_10_32_1","first-page":"33","article-title":"Intelligent prediction of RBC demand in trauma patients using decision tree methods","volume":"8","author":"Feng YN","year":"2021","journal-title":"Mil Med Res"},{"issue":"2","key":"e_1_2_10_33_1","first-page":"14","article-title":"Introduction to machine learning, neural networks, and deep learning","volume":"9","author":"Choi RY","year":"2020","journal-title":"Transl vis Sci Technol"},{"issue":"6","key":"e_1_2_10_34_1","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1111\/joim.12822","article-title":"eDoctor: machine learning and the future of medicine","volume":"284","author":"Handelman GS","year":"2018","journal-title":"J Intern Med"},{"issue":"4","key":"e_1_2_10_35_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.tmrv.2023.150758","article-title":"Optimizing RBC transfusion outcomes in patients with acute illness and in the chronic transfusion setting","volume":"37","author":"Fasano RM","year":"2023","journal-title":"Transfus Med Rev"}],"container-title":["Transfusion Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tme.70126","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/tme.70126","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tme.70126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:15:42Z","timestamp":1791357342000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/tme.70126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":34,"alternative-id":["10.1111\/tme.70126"],"URL":"https:\/\/doi.org\/10.1111\/tme.70126","archive":["Portico"],"relation":{},"ISSN":["0958-7578","1365-3148"],"issn-type":[{"value":"0958-7578","type":"print"},{"value":"1365-3148","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"assertion":[{"value":"2025-11-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"tme.70126"}}