Fig. 1From: Explainability of random survival forests in predicting conversion risk from mild cognitive impairment to Alzheimer’s diseasePerformance on test set of ML survival algorithms per timepoint: A Cox proportional hazard (CPH), B Random Survival Forests (RSF). On the left: plots over time of expected number of MCI patients at risk of conversion to AD, predicted survival curve in red, estimated survival curve by Kaplan–Meier in gray. On the right: prediction error curve calculated with Integrated Brier Score (IBS, critical cut-off limit of 0.25 in red). C-index on test set, cross-validated (cv) c-index on training set (mean ± standard deviation), root mean square error (RMSE) and median and mean absolute error are also reportedBack to article page