Classification and Interpretability of Mild Cognitive Impairment Based on Resting-State Functional Magnetic Resonance and Ensemble Learning

Table 3

Classification performance of XGBoost classifier.

	Accuracy (%)	AUC	Recall (%)	Precision (%)	F1-score	Kappa
DC	62.78	0.6558	40.00	60.00	0.4538	0.1803
fALFF	61.94	0.6608	53.33	58.33	0.5285	0.2086
mPerAF	65.14	0.6333	40.00	54.00	0.4243	0.2077
PerAF	57.78	0.5867	34.17	46.67	0.3802	0.0742
Wavelet-ALFF	63.33	0.6142	48.33	55.83	0.4833	0.2191