Fig. 12
From: Predicting sepsis onset in ICU using machine learning models: a systematic review and meta-analysis
Test set c-index. In the test set, the random forest model was the most frequently employed machine learning model with a c-index of 0.83 (0.82,0.83) in 5 studies. In terms of performance, both the random forest model (n = 5, c-index = 0.83 (0.82,0.83)) and XGBoost (n = 3, c-index = 0.83 (0.82,0.84)) exhibited similar performance. The rest are SVM(n = 3) with c-index 0.66 (0.56, 0.78) SAPS II (n = 2) with c-index 0.76(0.73,0.79) and SOFA(n = 3) with c-index 0.71(0.70,0.71)