biostudies-literatureUnknown55Gauss T<h4>Background</h4>Machine learning could improve the timely identification of trauma patients in need of hemorrhage control resuscitation (HCR), but the real-life performance remains unknown. The ShockMatrix study aimed to compare the predictive performance of a machine learning algorithm with that of clinicians in identifying the need for HCR.<h4>Methods</h4>Prospective, observational study in eight level-1 trauma centers. Upon receiving a prealert call, trauma clinicians in the resuscitation room entered nine predictor variables into a dedicated smartphone app and provided a subjective prediction of the need for HCR. These predictors matched those used in the machine learning model. The primary outcome, need for HCR, was defined as: transfusion in the resuscitation room, transfusion of The Lancet regional health. Europe101340https://www.ebi.ac.uk/biostudies/studies/S-EPMC12205608biostudies-literatureComparison of machine learning and human prediction to identify trauma patients in need of hemorrhage control resuscitation (ShockMatrix study): a prospective observational study.PMC12205608Rotival JJames AChristophe QGeeraerts TVilotitch AMathieu RAnatole HOlivier DNadal JPGosset PBrieu BSalah SGettes SBouillon JBAudibert GMeaudre Ede Cherisey HBouzat PLeone MAbback PSMorel JCaroline JHolleville MGay SKallel HEscudier EFloch TGaertner EJosse JMontalescaut ECollard CAlexandre BScotto MLegros VHigel NMedjkoune SMoyer JDNathalie DMathieu BRamonda VClavier TMeyer ATraumabase GroupHammad EYordanov YAnne GGauss TDavid JSLukaszewicz ACMermillod Blondin RHanouz JLJulien PBouhours GCesareo EJean FXLepetre PPopoff BWillig MBounes FPerez PWerner MMalec LJaillette CDelphine GMellati NLefrancois VFremery ABijok BDelhaye NPujo JCohen BDussau LJean PDuclos GColas CfalseComparison of machine learning and human prediction to identify trauma patients in need of hemorrhage control resuscitation (ShockMatrix study): a prospective observational study.<h4>Background</h4>Machine learning could improve the timely identification of trauma patients in need of hemorrhage control resuscitation (HCR), but the real-life performance remains unknown. The ShockMatrix study aimed to compare the predictive performance of a machine learning algorithm with that of clinicians in identifying the need for HCR.<h4>Methods</h4>Prospective, observational study in eight level-1 trauma centers. Upon receiving a prealert call, trauma clinicians in the resuscitation room entered nine predictor variables into a dedicated smartphone app and provided a subjective prediction of the need for HCR. These predictors matched those used in the machine learning model. The primary outcome, need for HCR, was defined as: transfusion in the resuscitation room, transfusion of 2025-01-01T00:00:00Z2025 Aug2026-06-03T07:37:35.413Z2026-04-26T03:10:15.573ZS-EPMC122056084058458910.1016/j.lanepe.2025.101340