. 2015 Nov 3;16(11):26303–26317. doi: 10.3390/ijms161125952

Table 3.

Evaluation parameters.

Parameter	Meaning	Expression
Accuracy (ACC)	Percentage of correct prediction	$A c c u r a c y = \frac{T P + T N}{T P + T N + F P + F N}$ ^a
Sensitivity	Percentage of correctly predicted positive	$S e n s i t i v i t y = \frac{T P}{T P + F N}$
Specificity	Percentage of correctly predicted negative	$S p e c i f c i t y = \frac{T N}{T N + F P}$
Strength	Mean value of the sum of sensitivity and specificity	$S t r e n g t h = \frac{S e n s i t i v i t y + S p e c i f c i t y}{2}$
MCC	Matthews correlation coefficient	$MCC = \frac{(T P \times T N) - (F N \times F P)}{\sqrt{(T P + F N) \times (T N + F P) \times (T P + F P) \times (T N + F N)}}$
Precision	Positive predictive rate	$P r e c i s i o n = \frac{T P}{T P + F P}$
F-measure	The harmonic mean of sensitivity and specificity	$F - measure = \frac{2 \times P r e s i o n \times S e n s i t i v i t y}{Presion + Sensitivity}$
AUC ^b	Probability that a classifier will rank a randomly chosen positive instance higher than a randomly chosen negative one	$A U C = \frac{\sum_{i - 1}^{n} T_{i}}{n T}$

^a TP = True positive number; TN = True negative number; FP = False positive number; FN = False negative number; ^b In AUC formulation, i takes on values from 1 to n, T is the total number of positives in the test set, and T_i is the number of positives that score higher than the ith highest scoring negative.