Table 1.

Evaluation measures.

Problem Type	Measure	Explanation
Classification	AUC	Area under the receiver operating characteristic (ROC) curve. The ROC curve is created by plotting the true positive rate (TPR) against the false positive rate (FPR) at various discrimination threshold settings for binary classifiers.
	SE	Sensitivity or true positive rate (TPR), is the fraction of actual positive cases that has been predicted as positive in the population. It is an evaluation measure for binary classifiers.
	SP	Specificity or true negative rate (TNR) refers to the fraction of true negative that has been predicted as negative in the population. It is an evaluation measure for binary classifier.
	ACC	Accuracy is the ratio of the number of correct predictions to the total number of input samples.
	PPV	Positive predictive value is the ratio of patients truly diagnosed as positive to all those who had positive test results. It is an evaluation measure for binary classifiers.
	NPV	Negative predictive value refers to the fraction of subjects truly diagnosed as negative among those who had negative test results. It is an evaluation measure for binary classifiers.
	Classification Precision	Same as PPV
	F1 score	It is defined as the harmonic mean of the precision and recall
	PLR	The Positive Likelihood Ratio is defined as the ratio between the true positivity rate and the false positivity rate.
	NLR	The Negative Likelihood Ratio is the opposite of the PLR.
Regression\Survival Analysis	DFS	Disease-Free Survival is defined as the time from randomization to recurrence of tumor or death.
	TTNT	Time-to-next treatment is defined as the time between baseline (randomization, inclusion or treatment initiation) and the date of subsequent systemic treatment initiation.
	C-index	Harrell’s concordance C-index: used to evaluate risk models in survival analysis. It is computed as the fraction of concordant patient pairs on the sum of concordant and discordant patient pairs, where two patients are considered concordant if the patient with the higher risk score is the one having a shorter time-to-disease.
	HR	In survival analysis, the hazard ratio is defined as the ratio of the hazard rates corresponding to the conditions described by two levels of an explanatory variable (e.g., cases vs. controls)