. 2021 May 6;13:633752. doi: 10.3389/fnagi.2021.633752

Table 3.

Performance metrics used in the evaluation of machine learning models.

Performance metric	Definition	Number of studies
Accuracy	$\frac{T P + T N}{T P + T N + F P + F N}$	174
Sensitivity (recall)	$\frac{T P}{T P + F N}$	110
Specificity (TNR)	$\frac{T N}{T N + F P}$	94
AUC	The two-dimensional area under the Receiver Operating Characteristic (ROC) curve	60
MCC	$\frac{T P \times T N - F P \times F N}{\sqrt{(T P + F P) (T P + F N) (T N + F P) (T N + F N)}}$	9
Precision (PPV)	$\frac{T P}{T P + F P}$	31
NPV	$\frac{T N}{T N + F N}$	8
F1 score	$2 \times \frac{p r e c i s i o n \times r e c a l l}{p r e c i s i o n + r e c a l l}$	25
Others (7 kappa; 4 error rate; 3 EER; 1 MSE; 1 LOR; 1 confusion matrix; 1 cross validation score; 1 YI; 1 FPR; 1 FNR; 1 G-mean; 1 PE; 5 combination of metrics)	N/A	28

TNR, true negative rate; AUC, Area under the ROC Curve; MCC, Matthews correlation coefficient; PPV, positive predictive value; NPV, negative predictive value; EER, equal error rate; MSE, mean squared error; LOR, log odds ratio; YI, Youden's Index; FPR, false positive rate; FNR, false negative rate; PE, probability excess.