Figure 1
From: Predicting outcomes of acute kidney injury in critically ill patients using machine learning
Study workflow for CKD prediction task. We utilized a population of patients from the observational follow-up data to train ML and statistical models to predict CKD after 3 and 6 months of developing AKI stage 3 in the ICU. 5-fold cross-validation was used to train and test models. Prediction performance was assessed with the AUROC and AUPR.
