External validation of an artificial intelligence model using clinical variables, including ICD-10 codes, for predicting in-hospital mortality among trauma patients: a multicenter retrospective cohort study
by Seungseok Lee, Do Wan Kim, Na-eun Oh, Hayeon Lee, Seoyoung Park, Dong Keon Yon, Wu Seong Kang , Jinseok Lee • 1 month ago
A multicenter retrospective cohort study validated an AI model utilizing ICD-10 codes and clinical variables to predict in-hospital mortality among trauma patients. Analyzing data from 4,439 patients, the model achieved an AUROC of 0.9448, outperforming traditional scoring systems like ISS and ICISS. It demonstrated high sensitivity and accuracy, particularly in lower-severity cases. The findings suggest the model's potential for enhancing patient triage and treatment protocols in emergency settings.