Fig. 6From: A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer’s DiseaseComparisons of cosine distances between the SHAP vectors of the first and last visits of the subjects for the diagnostic longitudinal categories: boxplots (top) and table with p values resulting from post-hoc analysis with average and standard deviations of probability scores for each category (bottom). p values in bold are statistically significantBack to article page