Fig. 2

Receiver operating characteristic (ROC) curves with 50% confidence interval of our best models with and without IMPACT features and the online International Mission for Prognosis And Clinical Trial Design (IMPACT) predictions of poor outcome (Extended Glasgow Outcome Scale 1–2) in the training set (38 patients) and validation set (19 patients). The red dots indicate the threshold at which the sensitivity and specificity are best. The area under the curve (AUC) of the model with IMPACT features was higher than our best model without those and similar to the impact predictor alone. The sensitivity and specificity of our best model with IMPACT parameters are slightly higher than those of the IMPACT predictor alone in both the training and the validation sets