{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:06:26Z","timestamp":1777633586305,"version":"3.51.4"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop an AutoML-based interpretable prediction model for blood transfusion requirements in severe traumatic brain injury (sTBI) patients, optimizing blood resource management through clinical-translational tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective cohort study (January 2020\u2013January 2025), 638 sTBI patients were enrolled. Random stratified sampling divided data into training (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f447) and testing (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f191) sets (7:3 ratio). We constructed an Automated Machine Learning (AutoML) framework using the Improved Hannibal Barca Optimizer (IHBO), which synchronously integrated LASSO feature selection verification and Shapley Additive exPlanations (SHAP) interpretability analysis. Model evaluation covered discriminative ability (AUC\/PR-AUC), calibration performance (Brier score), and clinical utility (Decision Curve Analysis).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The AutoML model demonstrated exceptional performance in the independent testing set, with ROC-AUC and PR-AUC values reflecting high predictive accuracy. It consistently outperformed comparator models across all metrics, including F1-score (0.8387), while DCA confirmed superior net benefit across clinically relevant thresholds. SHAP analysis identified nine key predictors hierarchically influencing transfusion risk: treatment type, GCS score, INR, K\n                      <jats:sup>+<\/jats:sup>\n                      , Ca2\n                      <jats:sup>+<\/jats:sup>\n                      , Hct, age, hemorrhagic shock, and skull fracture.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This explainable AutoML framework successfully deciphers multidimensional determinants of sTBI transfusion needs. The clinically deployable interactive system eliminates technical barriers through intuitive nine-feature input, establishing new paradigm for trauma care decision-support and blood resource optimization.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1757553","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T04:45:39Z","timestamp":1777437939000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of an automated machine learning-based prediction model and interactive tool for blood transfusion requirements in patients with severe traumatic brain injury"],"prefix":"10.3389","volume":"17","author":[{"given":"Chunhong","family":"Gong","sequence":"first","affiliation":[{"name":"Department of Blood Transfusion, Xianning Central Hospital, The First Affiliated Hospital of Hubei University of Science and Technology","place":["Xianning, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangli","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion, Xianning Central Hospital, The First Affiliated Hospital of Hubei University of Science and Technology","place":["Xianning, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Blood Transfusion, Xianning Central Hospital, The First Affiliated Hospital of Hubei University of Science and Technology","place":["Xianning, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"887","DOI":"10.4103\/NRR.NRR-D-24-01398","article-title":"Traumatic brain injury: bridging pathophysiological insights and precision treatment strategies","volume":"21","author":"Lu","year":"2025","journal-title":"Neural Regen Res"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1001\/jama.2024.20424","article-title":"Restrictive vs liberal transfusion strategy in patients with acute brain injury: the TRAIN randomized clinical trial","volume":"332","author":"Taccone","year":"2024","journal-title":"JAMA"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1186\/s13613-024-01411-1","article-title":"Efficacy of restrictive versus liberal transfusion strategies in patients with traumatic brain injury: a systematic review and meta-analysis of randomized controlled trials","volume":"14","author":"Yuan","year":"2024","journal-title":"Ann Intensive Care"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1016\/j.neubiorev.2021.08.029","article-title":"The biological significance and clinical utility of emerging blood biomarkers for traumatic brain injury","volume":"130","author":"Huibregtse","year":"2021","journal-title":"Neurosci Biobehav Rev"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"100891","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-associated circulatory overload","volume":"52","author":"Bulle","year":"2022","journal-title":"Blood Rev"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1186\/s13643-021-01703-8","article-title":"Red blood cell transfusion in animal models of acute brain injuries: a systematic review protocol","volume":"10","author":"Laflamme","year":"2021","journal-title":"Syst Rev"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1182\/blood.2025029042","article-title":"Counterpoint: the design and interpretation of blood transfusion randomized clinical trials","volume":"146","author":"Carson","year":"2025","journal-title":"Blood"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1513\/AnnalsATS.202109-1078OC","article-title":"Red blood cell transfusion at a Hemoglobin threshold of 7 g\/dl in critically ill patients: a regression discontinuity study","volume":"19","author":"Bosch","year":"2022","journal-title":"Ann Am Thorac Soc"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1097\/ALN.0000000000004139","article-title":"Personalized surgical transfusion risk prediction using machine learning to guide preoperative type and screen orders","volume":"137","author":"Lou","year":"2022","journal-title":"Anesthesiology"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"108495","DOI":"10.1016\/j.biotechadv.2024.108495","article-title":"Interpretable and explainable predictive machine learning models for data-driven protein engineering","volume":"79","author":"Medina-Ortiz","year":"2025","journal-title":"Biotechnol Adv"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"105216","DOI":"10.1016\/j.ijnurstu.2025.105216","article-title":"Nursing judgment in the age of generative artificial intelligence: a cross-national study on clinical decision-making performance among emergency nurses","volume":"172","author":"Levin","year":"2025","journal-title":"Int J Nurs Stud"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s40779-021-00326-3","article-title":"Intelligent prediction of RBC demand in trauma patients using decision tree methods","volume":"8","author":"Feng","year":"2021","journal-title":"Mil Med Res"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e963","DOI":"10.1097\/CCM.0000000000006585","article-title":"Transfusion practices in traumatic brain injury: a systematic review and meta-analysis of randomized controlled trials","volume":"53","author":"Larcipretti","year":"2025","journal-title":"Crit Care Med"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1055\/s-0041-1722970","article-title":"Fibrinolysis in traumatic brain injury: diagnosis, management, and clinical considerations","volume":"47","author":"Anderson","year":"2021","journal-title":"Semin Thromb Hemost"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/bs.acc.2025.01.003","article-title":"Coagulopathy prediction in traumatic brain injury","volume":"126","author":"Kalogirou","year":"2025","journal-title":"Adv Clin Chem"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.14336\/AD.202.0424","article-title":"Cellular components of the blood-brain barrier and their involvement in aging-associated cognitive impairment","volume":"16","author":"Shen","year":"2024","journal-title":"Aging Dis"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2714","DOI":"10.1182\/blood.2021011310","article-title":"Anticoagulation targeting membrane-bound anionic phospholipids improves outcomes of traumatic brain injury in mice","volume":"138","author":"Dong","year":"2021","journal-title":"Blood"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1186\/s13054-023-04541-3","article-title":"Trauma-induced disturbances in ionized calcium levels correlate parabolically with coagulopathy, transfusion, and mortality: a multicentre cohort analysis from the TraumaRegister DGU\u00ae","volume":"27","author":"Helsloot","year":"2023","journal-title":"Crit Care"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13017-024-00572-5","article-title":"Comparison of the lethal triad and the lethal diamond in severe trauma patients: a multicenter cohort","volume":"20","author":"Dupuy","year":"2025","journal-title":"World J Emerg Surg"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"101438","DOI":"10.1016\/j.accpm.2024.101438","article-title":"Hypocalcemia in critical care settings, from its clinical relevance to its treatment: a narrative review","volume":"43","author":"Fernandes","year":"2024","journal-title":"Anaesth Crit Care Pain Med"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1148\/rg.2021200189","article-title":"CT of Skull Base fractures: classification systems, complications, and management","volume":"41","author":"Dreizin","year":"2021","journal-title":"Radiographics"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"5228","DOI":"10.1097\/JS9.0000000000002599","article-title":"Re-exploration of the optimal threshold for restrictive transfusion after hip fracture: a multicenter prospective cohort","volume":"111","author":"Jiang","year":"2025","journal-title":"Int J Surg"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"4754","DOI":"10.1097\/JS9.0000000000001472","article-title":"Development and validation of models for predicting mortality in intertrochanteric fracture surgery patients with perioperative blood transfusion: a prospective multicenter cohort study","volume":"110","author":"Guo","year":"2024","journal-title":"Int J Surg"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1757553\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T04:45:41Z","timestamp":1777437941000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1757553\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":23,"alternative-id":["10.3389\/fneur.2026.1757553"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1757553","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"article-number":"1757553"}}