Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 12:55:101340.
doi: 10.1016/j.lanepe.2025.101340. eCollection 2025 Aug.

Comparison of machine learning and human prediction to identify trauma patients in need of hemorrhage control resuscitation (ShockMatrix study): a prospective observational study

Tobias Gauss  1   2 , Arthur James  3   4 , Clelia Colas  5 , Nathalie Delhaye  6 , Mathilde Holleville  7 , Benjamin Bijok  8 , Marie Werner  9   10 , Alain Meyer  11 , Véronique Ramonda  12 , Eric Cesareo  13 , Hugues de Cherisey  5 , Sofiane Medjkoune  5 , Samia Salah  1 , Jean-Pierre Nadal  14   15 , Jean-Denis Moyer  16 , Antoine Vilotitch  17 , Pierre Bouzat  1   2 , Julie Josse  18 ; Traumabase Group
Collaborators, Affiliations

Comparison of machine learning and human prediction to identify trauma patients in need of hemorrhage control resuscitation (ShockMatrix study): a prospective observational study

Tobias Gauss et al. Lancet Reg Health Eur. .

Abstract

Background: 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.

Methods: 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 more than four red blood cell units in 6 h of admission, any hemorrhage control procedure within 6 h, or death from hemorrhage within 24 h. The human and machine learning performances were assessed by sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and net clinical benefit. Human and machine learning agreement was assessed with Cohen's kappa coefficient.

Findings: Between August 2022 and June 2024, out of 5550 potential eligible patients, 1292 were ultimately included in the analyses. The need for HCR occurred in 170/1292 patients (13%). The results showed a positive likelihood ratio of 3.74 (95% confidence interval [CI]: 3.20-4.36) and a negative likelihood ratio of 0.36 (95% CI: 0.29-0.46) for the human prediction and a positive likelihood ratio of 4.01 (95% CI: 3.43-4.70) and negative likelihood ratio of 0.35 (95% CI: 0.38-0.44) for the machine learning prediction. The combined use of human and machine learning prediction yielded a sensitivity of 83% (95% CI: 77-88%) and a specificity of 73% (95% CI: 70-75%). The Cohen's kappa coefficient showed an agreement of 0.51 (95% CI: 0.48-0.55).

Interpretation: The prospective ShockMatrix temporal validation study suggests a comparable human and machine learning performance to predict the need for HCR using real-life and real-time information with a moderate level of agreement between the two. Machine learning enhanced decision awareness could potentially improve the detection of patients in need of HCR if used by clinicians.

Funding: The study received no funding.

Keywords: Decision support; Hemorrhage; Human decision making; Machine learning; Performance; Prediction; Trauma.

PubMed Disclaimer

Conflict of interest statement

TG reports honoraria from Laboratoire du Biomédicament Français and attending educational events organized by Octapharma; member of the scientific board Traumabase registry and French Society Anesthesia and Critical Care. Coordinator Traumatrix.fr Consortium. PB reports honoraria from Laboratoire du Biomédicament Français and is president of the National Trauma Committee (GITE). JDM received honoraria from Octapharma.

Figures

Fig. 1
Fig. 1
Study workflow. CT: Computer Tomogram; EMS: emergency medicine system; RESUS: resuscitation room; HIPAA: Health Insurance Portability and Accountability Act; HCR: Hemorrhage control resuscitation; ICU: Intensive Care Unit; OR: Operating Room.
Fig. 2
Fig. 2
Study flowchart. HCR: Hemorrhage control resuscitation.
See this image and copyright information in PMC

References

    1. Pelaccia T., Tardif J., Triby E., Charlin B. An analysis of clinical reasoning through a recent and comprehensive approach: the dual-process theory. Med Educ Online. 2011;16 doi: 10.3402/meo.v16i0.5890. - DOI - PMC - PubMed
    1. Durrands T.H., Murphy M., Wohlgemut J.M., De'Ath H.D., Perkins Z.B. Diagnostic accuracy of clinical examination for identification of life-threatening torsos injuries: a meta-analysis. Br J Surg. 2023;110:1885–1886. - PubMed
    1. Wohlgemut J.M., Marsden M.E.R., Stoner R.S., et al. Diagnostic accuracy of clinical examination to identify life- and limb-threatening injuries in trauma patients. Scand J Trauma Resusc Emerg Med. 2023;31:18. - PMC - PubMed
    1. Lindsay C., Davenport R., Baksaas-Aasen K., et al. Correction of trauma-induced coagulopathy by goal-directed therapy: a secondary analysis of the ITACTIC trial. Anesthesiology. 2024;141:904–912. - PMC - PubMed
    1. Clarke J.R., Trooskin S.Z., Doshi P.J., Greenwald L., Mode C.J. Time to laparotomy for intra-abdominal bleeding from trauma does affect survival for delays up to 90 minutes. J Trauma. 2002;52:420–425. - PubMed

LinkOut - more resources