Brain Informatics

Table 3 Performance metrics of the RF models

From: A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer’s Disease

Model	Accuracy	Specificity	Sensitivity	Precision	AUC
NC	\(74 \pm 4\%\)	\(84 \pm 3\%\)	\(73 \pm 4\%\)	\(70 \pm 8\%\)	0.88
MCI	\(75 \pm 3\%\)	\(75 \pm 4\%\)	\(75 \pm 4\%\)	\(70 \pm 7\%\)	0.82
AD	\(72 \pm 5\%\)	\(97 \pm 2\%\)	\(72 \pm 3\%\)	\(80 \pm 5\%\)	0.97
Global	\(75\%\)	\(85\%\)	\(74\%\)	\(73\%\)	0.89

Back to article page