Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study

Abstract Importance Decision-making in trauma patients remains challenging and often results in deviation from guidelines. Machine-Learning (ML) enhanced decision-support could improve hemorrhage resuscitation. Aim To develop a ML enhanced decision support tool to predict Need for Hemorrhage Resusci...

Full description

Saved in:
Bibliographic Details
Main Authors: Tobias Gauss, Jean-Denis Moyer, Clelia Colas, Manuel Pichon, Nathalie Delhaye, Marie Werner, Veronique Ramonda, Theophile Sempe, Sofiane Medjkoune, Julie Josse, Arthur James, Anatole Harrois, the Traumabase Group
Format: Article
Language:English
Published: BMC 2024-10-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-024-02723-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179863793631232
author Tobias Gauss
Jean-Denis Moyer
Clelia Colas
Manuel Pichon
Nathalie Delhaye
Marie Werner
Veronique Ramonda
Theophile Sempe
Sofiane Medjkoune
Julie Josse
Arthur James
Anatole Harrois
the Traumabase Group
author_facet Tobias Gauss
Jean-Denis Moyer
Clelia Colas
Manuel Pichon
Nathalie Delhaye
Marie Werner
Veronique Ramonda
Theophile Sempe
Sofiane Medjkoune
Julie Josse
Arthur James
Anatole Harrois
the Traumabase Group
author_sort Tobias Gauss
collection DOAJ
description Abstract Importance Decision-making in trauma patients remains challenging and often results in deviation from guidelines. Machine-Learning (ML) enhanced decision-support could improve hemorrhage resuscitation. Aim To develop a ML enhanced decision support tool to predict Need for Hemorrhage Resuscitation (NHR) (part I) and test the collection of the predictor variables in real time in a smartphone app (part II). Design, setting, and participants Development of a ML model from a registry to predict NHR relying exclusively on prehospital predictors. Several models and imputation techniques were tested. Assess the feasibility to collect the predictors of the model in a customized smartphone app during prealert and generate a prediction in four level-1 trauma centers to compare the predictions to the gestalt of the trauma leader. Main outcomes and measures Part 1: Model output was NHR defined by 1) at least one RBC transfusion in resuscitation, 2) transfusion ≥ 4 RBC within 6 h, 3) any hemorrhage control procedure within 6 h or 4) death from hemorrhage within 24 h. The performance metric was the F4-score and compared to reference scores (RED FLAG, ABC). In part 2, the model and clinician prediction were compared with Likelihood Ratios (LR). Results From 36,325 eligible patients in the registry (Nov 2010—May 2022), 28,614 were included in the model development (Part 1). Median age was 36 [25–52], median ISS 13 [5–22], 3249/28614 (11%) corresponded to the definition of NHR. A XGBoost model with nine prehospital variables generated the best predictive performance for NHR according to the F4-score with a score of 0.76 [0.73–0.78]. Over a 3-month period (Aug—Oct 2022), 139 of 391 eligible patients were included in part II (38.5%), 22/139 with NHR. Clinician satisfaction was high, no workflow disruption observed and LRs comparable between the model and the clinicians. Conclusions and relevance The ShockMatrix pilot study developed a simple ML-enhanced NHR prediction tool demonstrating a comparable performance to clinical reference scores and clinicians. Collecting the predictor variables in real-time on prealert was feasible and caused no workflow disruption.
format Article
id doaj-art-6c0cc9baa3124d98950b4a3b9984b28f
institution OA Journals
issn 1472-6947
language English
publishDate 2024-10-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-6c0cc9baa3124d98950b4a3b9984b28f2025-08-20T02:18:24ZengBMCBMC Medical Informatics and Decision Making1472-69472024-10-0124111310.1186/s12911-024-02723-9Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot studyTobias Gauss0Jean-Denis Moyer1Clelia Colas2Manuel Pichon3Nathalie Delhaye4Marie Werner5Veronique Ramonda6Theophile Sempe7Sofiane Medjkoune8Julie Josse9Arthur James10Anatole Harrois11the Traumabase Group12Service Anesthésie-Réanimation, CHU Grenoble AlpesService Anesthésie-Réanimation, CHU CaenCap Gemini InventService Anesthésie-Réanimation, CHU Toulouse, Toulouse III – Université Paul SabatierService Anesthésie-Réanimation, Hôpital Européen Georges PompidouService d’Anesthésie Réanimation Chirurgicale, DMU 12 Anesthésie Réanimation Chirurgicale Médecine Péri‐Opératoire et Douleur Hôpital Bicêtre, AP‐HP, Université Paris‐SaclayPôle Anesthésie, Service de Réanimation Polyvalente URM Purpan, CHU ToulouseCap Gemini InventCap Gemini InventInstitut National de Recherche en Sciences Et Technologies du Numérique, Premedical Team, Université de MontpellierDMU DREAM, Service Anesthésie-Réanimation, Hôpital Pitié-Salpétrière, Sorbonne UniversitéService d’Anesthésie Réanimation Chirurgicale, DMU 12 Anesthésie Réanimation Chirurgicale Médecine Péri‐Opératoire et Douleur Hôpital Bicêtre, AP‐HP, Université Paris‐SaclayThe Traumabase Group, Hôpital Beaujon, AP-HPAbstract Importance Decision-making in trauma patients remains challenging and often results in deviation from guidelines. Machine-Learning (ML) enhanced decision-support could improve hemorrhage resuscitation. Aim To develop a ML enhanced decision support tool to predict Need for Hemorrhage Resuscitation (NHR) (part I) and test the collection of the predictor variables in real time in a smartphone app (part II). Design, setting, and participants Development of a ML model from a registry to predict NHR relying exclusively on prehospital predictors. Several models and imputation techniques were tested. Assess the feasibility to collect the predictors of the model in a customized smartphone app during prealert and generate a prediction in four level-1 trauma centers to compare the predictions to the gestalt of the trauma leader. Main outcomes and measures Part 1: Model output was NHR defined by 1) at least one RBC transfusion in resuscitation, 2) transfusion ≥ 4 RBC within 6 h, 3) any hemorrhage control procedure within 6 h or 4) death from hemorrhage within 24 h. The performance metric was the F4-score and compared to reference scores (RED FLAG, ABC). In part 2, the model and clinician prediction were compared with Likelihood Ratios (LR). Results From 36,325 eligible patients in the registry (Nov 2010—May 2022), 28,614 were included in the model development (Part 1). Median age was 36 [25–52], median ISS 13 [5–22], 3249/28614 (11%) corresponded to the definition of NHR. A XGBoost model with nine prehospital variables generated the best predictive performance for NHR according to the F4-score with a score of 0.76 [0.73–0.78]. Over a 3-month period (Aug—Oct 2022), 139 of 391 eligible patients were included in part II (38.5%), 22/139 with NHR. Clinician satisfaction was high, no workflow disruption observed and LRs comparable between the model and the clinicians. Conclusions and relevance The ShockMatrix pilot study developed a simple ML-enhanced NHR prediction tool demonstrating a comparable performance to clinical reference scores and clinicians. Collecting the predictor variables in real-time on prealert was feasible and caused no workflow disruption.https://doi.org/10.1186/s12911-024-02723-9TraumaShockPrediction toolMachine LearningDecision Support
spellingShingle Tobias Gauss
Jean-Denis Moyer
Clelia Colas
Manuel Pichon
Nathalie Delhaye
Marie Werner
Veronique Ramonda
Theophile Sempe
Sofiane Medjkoune
Julie Josse
Arthur James
Anatole Harrois
the Traumabase Group
Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
BMC Medical Informatics and Decision Making
Trauma
Shock
Prediction tool
Machine Learning
Decision Support
title Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
title_full Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
title_fullStr Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
title_full_unstemmed Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
title_short Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study
title_sort pilot deployment of a machine learning enhanced prediction of need for hemorrhage resuscitation after trauma the shockmatrix pilot study
topic Trauma
Shock
Prediction tool
Machine Learning
Decision Support
url https://doi.org/10.1186/s12911-024-02723-9
work_keys_str_mv AT tobiasgauss pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT jeandenismoyer pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT cleliacolas pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT manuelpichon pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT nathaliedelhaye pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT mariewerner pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT veroniqueramonda pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT theophilesempe pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT sofianemedjkoune pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT juliejosse pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT arthurjames pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT anatoleharrois pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy
AT thetraumabasegroup pilotdeploymentofamachinelearningenhancedpredictionofneedforhemorrhageresuscitationaftertraumatheshockmatrixpilotstudy