Table 2.

Common measures used in this paper to gauge the performance of classification tasks. In the formulae above, TP (True Positives) is the number of correctly classified concussed individuals; TN (True Negatives) is the number of correctly classified control participants; while FP and FN are the numbers of falsely classified control (i.e. False Positives) and concussed (i.e. False Negatives) participants, respectively.

Performance Metric	Definition	Alternate name
Accuracy	$\frac{\mathrm{TP}+\mathrm{TN}}{\mathrm{TP}+\mathrm{TN}+\mathrm{FP}+\mathrm{FN}}$
Recall	$\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FN}}$	also True Positive Rate (TPR)
Precision	$\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FP}}$	also Positive Predictive Value (PPV)
Specificity	$\frac{\mathrm{TN}}{\mathrm{TN}+\mathrm{FP}}$	also True Negative Rate (TNR)
Miss Rate	$\frac{\mathrm{FN}}{\mathrm{FN}+\mathrm{TP}}$	also False Negative Rate (FNR)	$FNR\equiv 1-TPR$
False Discovery Rate (FDR)	$\frac{\mathrm{FP}}{\mathrm{FP}+\mathrm{TP}}$		$FDR\equiv 1-PPV$
False Positive Rate (FPR)	$\frac{\mathrm{FP}}{\mathrm{FP}+\mathrm{TN}}$		$FPR\equiv 1-TNR$
Negative Predictive Value (NPV)	$\frac{\mathrm{TN}}{\mathrm{FN}+\mathrm{TN}}$
Informedness	$TPR+TNR-1$
Markedness	$PPV+NPV-1$