Figure 3
From: Predicting outcomes of acute kidney injury in critically ill patients using machine learning
Performance of the Random Forest and Logistic regression model. (a) Receiver operating characteristic and Precision-recall curves for estimating the discrimination between the Logistic regression model and the Random Forest model in the prediction of CKD three months after developing AKI. There are 75 subjects in this analysis from whom 63% developed CKD. (b) Receiver operating characteristic and Precision-recall curves for estimating the discrimination between the Logistic regression model and the Random Forest model in the prediction of CKD six months after developing AKI. There are 53 subjects in this analysis from whom 62% of them developed CKD.
