Table 1

A 2×2 table showing the cross-classification of index test and reference standard results and overview of measures of accuracy that can be calculated from these data*

Embedded Image
True positivesPeople with the target condition who have a positive test resultTP
True negativesPeople without the target condition who have a negative test resultTN
False positivesPeople without the target condition who have a positive test resultFP
False negativesPeople with the target condition who have a negative test resultFN
SensitivityProportion of patients with the target condition who have a positive test resultTP/(TP+FN)
SpecificityProportion of patients without the target condition who have a negative test resultTN/(FP+TN)
Positive predictive value (PPV)Probability that a patient with a positive test result has the target conditionTP/(TP+FP)
Negative predictive value (NPV)Probability that a patient with a negative test result does not have the target conditionTN/(FN+TN)
PrevalenceThe proportion of patients in the whole study population who have the target condition(TP+FN)/(TP+FP+FN+TN)
Positive likelihood ratio (LR+)The number of times more likely a person with the target condition is to have a positive test result compared with a person without the target condition(TP/(TP+FN))/(FP/(FP+TN)) or sensitivity/(1−specificity)
Negative likelihood ratio (LR−)The number of times more likely a person with the target condition is to have a negative test result compared with a person without the target condition(FN/(TP+FN))/(TN/(FP+TN)) or (1−sensitivity)/specificity
  • *Adapted from Whiting P, Martin RM, Ben-Shlomo Y, et al. How to apply the results of a research paper on diagnosis to your patient. JRSM Short Reports 2013;4:7.

  • FN, False negatives; TP, true positives.