Fig. 10From: Predicting sepsis onset in ICU using machine learning models: a systematic review and meta-analysisTrain set c-index. In the train set, XGBoost (bottom) was the most frequently utilized machine learning model with a c-index of 0.83 (0.83,0.84) in 7 studies. The rest are RF(n = 6) SAPS II(n = 3) and SOFA(n = 4), the C-index of them are 0.79 (0.78,0.79) 0.70(0.70,0.70) and 0.66(0.66,0.66)Back to article page