Humans versus machine learning models: improving the outcome of trauma patients

Trauma is a leading cause of death among young adults worldwide. Prompt and effective haemorrhage control is essential for improving outcomes, and any delay must be avoided.1 In this context, tools such as Artificial Intelligence (AI)-based clinical decision support systems which can enable more rapid and accurate decision-making may be life-saving.2,3 In this issue of The Lancet Regional Health – Europe, Gauss and colleagues present a prospective study describing the performance of a machine learning (ML) model that predicts the need for haemorrhage control resuscitation (HCR) in patients referred to 8 Level-1 centres in France.