Figure 3 | Scientific Reports

Figure 3

From: Machine learning algorithms for identifying predictive variables of mortality risk following dementia diagnosis: a longitudinal cohort study

Figure 3Figure 3

(A) ROC curve for all selected features by Elastic net-logistic regression classifier for predicting mortality risk based on the testing set (AUROC: 73.35%, 95% C.I 72.25–74.36%). (B) ROC curve for all selected features by SCAD-SVM classifier for predicting mortality risk based on the testing set (AUROC: 73.75%, 95% C.I: 72.64–74.75%). (C) ROC curve for MCP- neural network classifier for predicting mortality risk based on the testing set (AUROC: 72.95%, 95% C.I 71.85–73.95%).

Back to article page