Table 5.

Comparison of predictability

				In relapse
	Accuracy	AUC	κ‐statistic	TPR	TNR	FPR	FNR
Niigata group (Training set)	78.4%	0.746	0.508	0.627	0.866	0.134	0.373
Nagaoka group (Validation set)	71.0%	0.667	0.274	0.500	0.784	0.216	0.500

In this prediction model, true‐positive rate (TPR, also called the sensitivity) and false‐positive rate (FNR, it shows miss rate) in relapse were not sufficiently. However, true–negative rate (TNR, also called specificity) was high‐ and false‐positive rate (FPR, it means probability of false alarm) in relapse was very low. Therefore, clinicians may consider changes in treatment options if relapse is predicted.

AUC; area under the curve, Accuracy = (true positive + true negative)/ all, TPR = true positive/ (true positive + false negative) = 1‐FNR, FNR = false negative/ (false negative + true positive) = 1‐TPR, TNR = true negative/ (true negative + false positive) = 1‐ FPR, FPR = false positive/ (false positive + true negative) = 1‐TNR.