Table 7.

Evaluation metrics.

Metric	Definition	Formula
True positive (TP)	The number of samples which were predicted positive and actually positive	The number of sick patients correctly classified out of the 17 positive samples
False positive (FP)	The number of samples which were predicted positive and actually negative	The number of sick patients that were incorrectly classified out of the 17 positive samples
True negative (TN)	The number of samples which were predicted negative and actually negative	The number of healthy patients correctly classified out of the 31 negative samples
False negative (FN)	The number of samples which were predicted negative and actually positive	The number of healthy patients incorrectly classified out of the 31 negative samples
Accuracy	The proportion of correct classifications	(TP +TN )/( TN +TP +FN +FP)
Sensitivity (recall)	The proportion of the positive class that got correctly classified	(TP)/(TP+FN)
Specificity	The proportion of the negative class that got correctly classified	(TN)/(TN+FP)
Precision	How good a model is at predicting the positive class	(TP)/(TP+FP)