{Reference Type}: Journal Article
{Title}: External Validation of Predictors of Mortality in Polytrauma Patients.
{Author}: Becker ER;Price AD;Barth J;Hong S;Chowdhry V;Starr AJ;Sagi HC;Park C;Goodman MD;
{Journal}: J Surg Res
{Volume}: 301
{Issue}: 0
{Year}: 2024 Aug 1
{Factor}: 2.417
{DOI}: 10.1016/j.jss.2024.07.024
{Abstract}: <B>BACKGROUND: </B>The Parkland Trauma Index of Mortality (PTIM) is an integrated, machine learning 72-h mortality prediction model that automatically extracts and analyzes demographic, laboratory, and physiological data in polytrauma patients. We hypothesized that this validated model would perform equally as well at another level 1 trauma center.<BR><B>METHODS: </B>A retrospective cohort study was performed including ∼5000 adult level 1 trauma activation patients from January 2022 to September 2023. Demographics, physiologic and laboratory values were collected. First, a test set of models using PTIM clinical variables (CVs) was used as external validation, named PTIM+. Then, multiple novel mortality prediction models were developed considering all CVs designated as the Cincinnati Trauma Index of Mortality (CTIM). The statistical performance of the models was then compared.<BR><B>RESULTS: </B>PTIM CVs were found to have similar predictive performance within the PTIM + external validation model. The highest correlating CVs used in CTIM overlapped considerably with those of the PTIM, and performance was comparable between models. Specifically, for prediction of mortality within 48 h (CTIM versus PTIM): positive prediction value was 35.6% versus 32.5%, negative prediction value was 99.6% versus 99.3%, sensitivity was 81.0% versus 82.5%, specificity was 97.3% versus 93.6%, and area under the curve was 0.98 versus 0.94.<BR><B>CONCLUSIONS: </B>This external cohort study suggests that the variables initially identified via PTIM retain their predictive ability and are accessible in a different level 1 trauma center. This work shows that a trauma center may be able to operationalize an effective predictive model without undertaking a repeated time and resource intensive process of full variable selection.