Fig. 2From: A machine learning approach using endpoint adjudication committee labels for the identification of sepsis predictors at the emergency departmentVariable importance of both the base (logistic regression with demographic and vital variables) and the extended L1 (L1 lasso with all data) models. Dots represent the learned coefficient in the trained models in the outer loop of the DLCV. The numbers indicate the number of times a variable was selected in the trained model in the outer loop of the DLCV. Only variables selected more than 7 times are shownBack to article page