Prediction of survival in out-of-hospital cardiac arrest: The updated SCARS Model

Abstract

Out-of-hospital cardiac arrest (OHCA) is a major health concern worldwide. Although one third of all cases achieve return of spontaneous circulation (ROSC) and may undergo a difficult period in the ICU, only one in ten survive. This study aimed to improve our previously developed machine learning model for early prognostication of survival in OHCA. We studied all cases registered in the Swedish Cardiopulmonary Resuscitation Registry during 2010 and 2020 (n=55,615). We compared the predictive performance of extreme gradient boosting (XGB), LightGBM, logistic regression, CatBoost, random forest and TabNet. For each framework, we developed models that optimized (1) a weighted F1 score to penalize models that yielded more false negatives, and (2) PR AUC (precision recall area under the curve). LightGBM assigned higher importance values to a larger set of variables, while XGB made predictions using fewer predictors. The AUC ROC scores for LightGBM was 0.958 (optimized for weighted F1) and 0.961 (optimized for PR AUC), while for XGB, the scores were 0.958 and 0.960 respectively. The calibration plots showed subtle underestimation of survival for LightGBM, contrasting with a mild overestimation for XGB models. In the crucial range of 0 to 10% likelihood of survival, the XGB model, optimized with PR AUC, emerged as a clinically safe model. We improved our previous prediction model by creating a parsimonious model with AUC ROC at 0.96, with excellent calibration and no apparent risk of underestimating survival in the critical probability range (0-10%). The model is available at www.gocares.se.