MmisAT and MmisP: an efficient and accurate suite of variant analysis toolkit for primary mitochondrial diseases

Table 2 Performance of various algorithmic models

Methods	Accuracy (%)	Precision (%)	AUC	F1Score	Recall (%)	MCC
AdaBoost	80.91	78.84	0.874	0.817	85.01	0.631
Decision Tree	74.30	77.17	0.743	0.727	68.90	0.646
Random Forest	80.96	82.75	0.877	0.802	78.15	0.744
Logistic Regression	81.92	82.01	0.904	0.819	81.92	0.725
KNeighbors	71.25	71.30	0.789	0.710	71.08	0.587
SVM	79.83	81.45	0.880	0.792	77.32	0.711

ISSN: 1479-7364