{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T07:27:32Z","timestamp":1770881252608,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CIDMA, The Center for Research and Development in Mathematics and Applications of the University of Aveiro, and the Portuguese Foundation for Science and Technology (FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia)","award":["UIDB\/04106\/2020"],"award-info":[{"award-number":["UIDB\/04106\/2020"]}]},{"name":"CIDMA, The Center for Research and Development in Mathematics and Applications of the University of Aveiro, and the Portuguese Foundation for Science and Technology (FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia)","award":["UIDP\/04106\/2020"],"award-info":[{"award-number":["UIDP\/04106\/2020"]}]},{"name":"Thematic Line Biomathematics of CIDMA","award":["UIDB\/04106\/2020"],"award-info":[{"award-number":["UIDB\/04106\/2020"]}]},{"name":"Thematic Line Biomathematics of CIDMA","award":["UIDP\/04106\/2020"],"award-info":[{"award-number":["UIDP\/04106\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MCA"],"abstract":"<jats:p>The benefits of Patient Blood Management can vary depending on a patient\u2019s risk profile for requiring a blood transfusion. The objective of this study is to develop and analyse machine learning models that can identify patients at risk of requiring red blood cell transfusion. This retrospective cohort study was conducted at a tertiary northern Portuguese hospital between 2018 and 2023. Two machine learning algorithms, extreme gradient boosting and neural networks, were employed due to their efficiency in handling complex feature interactions. Shapley additive explanations values were analysed to assess the contribution of each feature to the predictions generated by the models. The neural network achieved an accuracy of 0.735 and an area under the receiver operating characteristic curve of 0.798 (95% CI 0.747 to 0.849). The extreme gradient boosting model achieved an accuracy of 0.700 and an area under the receiver operating characteristic curve of 0.762 (95% CI 0.707 to 0.817). An analysis of Shapley additive explanations values revealed that the most important variable was preoperative haemoglobin levels, which can be optimised through the Patient Blood Management approach. These machine learning models demonstrate the potential to improve the accuracy of transfusion prediction at hospital admission, despite the absence of key variables such as surgeon identity and anaemia diagnosis.<\/jats:p>","DOI":"10.3390\/mca30020022","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T10:04:28Z","timestamp":1740391468000},"page":"22","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting Red Blood Cell Transfusion in Elective Cardiac Surgery: A Machine Learning Approach"],"prefix":"10.3390","volume":"30","author":[{"given":"Beatriz","family":"Lau","sequence":"first","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"}]},{"given":"Daniel","family":"Ramos","sequence":"additional","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1051-8084","authenticated-orcid":false,"given":"Vera","family":"Afreixo","sequence":"additional","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9677-4315","authenticated-orcid":false,"given":"Lu\u00eds M.","family":"Silva","sequence":"additional","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4632-3561","authenticated-orcid":false,"given":"Ana Helena","family":"Tavares","sequence":"additional","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5450-7374","authenticated-orcid":false,"given":"Miguel Martins","family":"Felgueiras","sequence":"additional","affiliation":[{"name":"Centre for Research and Development in Mathematics and Applications, University of Aveiro, 3810-193 Aveiro, Portugal"},{"name":"Polytechnic of Leiria and Centre for Statistics and Applications, University of Leiria, 2411-901 Leiria, Portugal"}]},{"given":"Diana","family":"Castro Paup\u00e9rio","sequence":"additional","affiliation":[{"name":"Local Health Unit of Vila Nova de Gaia Espinho, 4434-502 Vila Nova de Gaia, Portugal"},{"name":"Egas Moniz Health Alliance Academic Clinical Centre, 3810-193 Aveiro, Portugal"}]},{"given":"Jo\u00e3o","family":"Firmino-Machado","sequence":"additional","affiliation":[{"name":"Local Health Unit of Vila Nova de Gaia Espinho, 4434-502 Vila Nova de Gaia, Portugal"},{"name":"Egas Moniz Health Alliance Academic Clinical Centre, 3810-193 Aveiro, Portugal"},{"name":"Department of Medical Sciences, University of Aveiro, 3810-193 Aveiro, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1053\/j.jvca.2017.06.026","article-title":"2017 EACTS\/EACTA Guidelines on Patient Blood Management for Adult Cardiac Surgery","volume":"32","author":"Boer","year":"2018","journal-title":"J. Cardiothorac. Vasc. Anesth."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.athoracsur.2013.07.020","article-title":"Transfusion of 1 and 2 Units of Red Blood Cells Is Associated With Increased Morbidity and Mortality","volume":"97","author":"Paone","year":"2014","journal-title":"Ann. Thorac. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1016\/j.athoracsur.2013.08.016","article-title":"Blood Transfusions in Cardiac Surgery: Indications, Risks, and Conservation Strategies","volume":"97","author":"Kilic","year":"2014","journal-title":"Ann. Thorac. Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1213\/ANE.0000000000002549","article-title":"Perioperative Patient Blood Management to Improve Outcomes","volume":"127","author":"Desai","year":"2018","journal-title":"Anesth. Analg."},{"key":"ref_5","unstructured":"World Health Organization (2021). The Urgent Need to Implement Patient Blood Management: Policy Brief, World Health Organization."},{"key":"ref_6","first-page":"476","article-title":"A Global Definition of Patient Blood Management","volume":"135","author":"Shander","year":"2022","journal-title":"Anesth. Analg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1097\/ALN.0b013e318254d1a3","article-title":"Patient Blood Management","volume":"116","author":"Goodnough","year":"2012","journal-title":"Anesthesiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1093\/bja\/aex205","article-title":"The ACTA PORT-Score for Predicting Perioperative Risk of Blood Transfusion for Adult Cardiac Surgery","volume":"119","author":"Klein","year":"2017","journal-title":"Br. J. Anaesth."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s12178-020-09600-8","article-title":"Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions","volume":"13","author":"Helm","year":"2020","journal-title":"Curr. Rev. Musculoskelet. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1111\/trf.15935","article-title":"Machine Learning\u2013Based Prediction of Transfusion","volume":"60","author":"Mitterecker","year":"2020","journal-title":"Transfusion"},{"key":"ref_11","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","year":"2022","journal-title":"Anesth. Analg."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mavrogiorgou, A., Kiourtis, A., Kleftakis, S., Mavrogiorgos, K., Zafeiropoulos, N., and Kyriazis, D. (2022). A Catalogue of Machine Learning Algorithms for Healthcare Risk Predictions. Sensors, 22.","DOI":"10.3390\/s22228615"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1016\/j.bbe.2021.04.015","article-title":"Extreme Gradient Boosting Machine Learning Method for Predicting Medical Treatment in Patients with Acute Bronchiolitis","volume":"41","author":"Mateo","year":"2021","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2753","DOI":"10.1111\/trf.12723","article-title":"Restrictive Blood Transfusion Practices Are Associated with Improved Patient Outcomes","volume":"54","author":"Goodnough","year":"2014","journal-title":"Transfusion"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1097\/EJA.0000000000001721","article-title":"Machine Learning-Based Prediction of Massive Perioperative Allogeneic Blood Transfusion in Cardiac Surgery","volume":"39","author":"Tschoellitsch","year":"2022","journal-title":"Eur. J. Anaesthesiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e100245","DOI":"10.1136\/bmjhci-2020-100245","article-title":"Artificial Intelligence-Based Prediction of Transfusion in the Intensive Care Unit in Patients with Gastrointestinal Bleeding","volume":"28","author":"Levi","year":"2021","journal-title":"BMJ Health Care Inform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.ejvs.2016.12.016","article-title":"Predicting the Need for Intra-Operative Large Volume Blood Transfusions During Thoraco-Abdominal Aortic Aneurysm Repair","volume":"53","author":"Pieri","year":"2017","journal-title":"Eur. J. Vasc. Endovasc. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7911","DOI":"10.1080\/14767058.2021.1937992","article-title":"Predicting the Need for Blood Transfusion Requirement in Postpartum Hemorrhage","volume":"35","author":"Attali","year":"2024","journal-title":"J. Matern.-Fetal Neonatal Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1007\/s00264-013-1795-7","article-title":"Predicting the Need for Blood Transfusion in Patients with Hip Fractures","volume":"37","author":"Kadar","year":"2013","journal-title":"Int. Orthop."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105343","DOI":"10.1016\/j.ijmedinf.2024.105343","article-title":"Development and Validation of a Machine Learning Prediction Model for Perioperative Red Blood Cell Transfusions in Cardiac Surgery","volume":"184","author":"Li","year":"2024","journal-title":"Int. J. Med. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhe, S., Zimmerman, J., Morrisey, C., Tonna, J.E., Sharma, V., and Metcalf, R.A. (2022). Development and Validation of a Machine Learning Method to Predict Intraoperative Red Blood Cell Transfusions in Cardiothoracic Surgery. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-05445-y"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"530","DOI":"10.21037\/atm-20-7375","article-title":"Machine Learning Models to Predict Red Blood Cell Transfusion in Patients Undergoing Mitral Valve Surgery","volume":"9","author":"Liu","year":"2021","journal-title":"Ann. Transl. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107798","DOI":"10.1016\/j.isci.2023.107798","article-title":"A Model Based on Electronic Health Records to Predict Transfusion Events in On-Pump Cardiac Surgery","volume":"26","author":"Chen","year":"2023","journal-title":"iScience"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1111\/j.1423-0410.2009.01160.x","article-title":"Predicting Transfusions in Cardiac Surgery: The Easier, the Better: The Transfusion Risk and Clinical Knowledge Score","volume":"96","author":"Ranucci","year":"2009","journal-title":"Vox Sang."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"31","DOI":"10.4103\/sja.SJA_543_18","article-title":"The STROBE Guidelines","volume":"13","author":"Cuschieri","year":"2019","journal-title":"Saudi J. Anaesth."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100799","DOI":"10.1016\/j.imu.2021.100799","article-title":"Missing Value Imputation Affects the Performance of Machine Learning: A Review and Analysis of the Literature (2010\u20132021)","volume":"27","author":"Hasan","year":"2021","journal-title":"Inform. Med. Unlocked"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple Imputation by Chained Equations: What Is It and How Does It Work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","article-title":"The Class Imbalance Problem: A Systematic Study","volume":"6","author":"Japkowicz","year":"2002","journal-title":"Intell. Data Anal."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-Sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"102119","DOI":"10.1016\/j.mex.2023.102119","article-title":"An Optimized XGBoost-Based Machine Learning Method for Predicting Wave Run-up on a Sloping Beach","volume":"10","author":"Tarwidi","year":"2023","journal-title":"MethodsX"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"122843","DOI":"10.1016\/j.jclepro.2020.122843","article-title":"Deep Learning Model for Demolition Waste Prediction in a Circular Economy","volume":"274","author":"Akanbi","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1007\/s10822-020-00314-0","article-title":"Interpretation of Machine Learning Models Using Shapley Values: Application to Compound Potency and Multi-Target Activity Predictions","volume":"34","author":"Bajorath","year":"2020","journal-title":"J. Comput. Aided Mol. Des."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1111\/j.1537-2995.2006.00860.x","article-title":"Development and Validation of Transfusion Risk Understanding Scoring Tool (TRUST) to Stratify Cardiac Surgery Patients According to Their Blood Transfusion Needs","volume":"46","author":"Alghamdi","year":"2006","journal-title":"Transfusion"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/S1010-7940(02)00372-X","article-title":"Reduction of the Inflammatory Response Following Coronary Bypass Grafting with Total Minimal Extracorporeal Circulation","volume":"22","author":"Fromes","year":"2002","journal-title":"Eur. J. Cardio-Thorac. Surg."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.bpa.2015.03.001","article-title":"Inflammatory Response and Extracorporeal Circulation","volume":"29","author":"Kraft","year":"2015","journal-title":"Best. Pract. Res. Clin. Anaesthesiol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.ejcts.2006.01.053","article-title":"Comparison of the Inflammatory Response between Miniaturized and Standard CPB Circuits in Aortic Valve Surgery","volume":"29","author":"Bical","year":"2006","journal-title":"Eur. J. Cardio-Thorac. Surg."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1007\/BF03022795","article-title":"Prediction of Massive Blood Transfusion in Cardiac Surgery","volume":"53","author":"Karkouti","year":"2006","journal-title":"Can. J. Anesth.\/J. Can. D\u2019anesth\u00e9sie"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"S27","DOI":"10.1016\/j.athoracsur.2007.02.099","article-title":"Perioperative Blood Transfusion and Blood Conservation in Cardiac Surgery: The Society of Thoracic Surgeons and The Society of Cardiovascular Anesthesiologists Clinical Practice Guideline","volume":"83","author":"Ferraris","year":"2007","journal-title":"Ann. Thorac. Surg."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1111\/j.1537-2995.2004.04144.x","article-title":"The Independent Association of Massive Blood Loss with Mortality in Cardiac Surgery","volume":"44","author":"Karkouti","year":"2004","journal-title":"Transfusion"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1111\/anae.14466","article-title":"Optimisation of Pre-Operative Anaemia in Patients before Elective Major Surgery\u2014Why, Who, When and How?","volume":"74","author":"Munting","year":"2019","journal-title":"Anaesthesia"}],"container-title":["Mathematical and Computational Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2297-8747\/30\/2\/22\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:41:37Z","timestamp":1760028097000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2297-8747\/30\/2\/22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,24]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["mca30020022"],"URL":"https:\/\/doi.org\/10.3390\/mca30020022","relation":{},"ISSN":["2297-8747"],"issn-type":[{"value":"2297-8747","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,24]]}}}