Sensitivity, specificity, positive and negative predictive value
What does it mean that a screening test has a sensitivity of 80 % and a specificity of 80 %? What conclusion can be drawn as to the probability of a patient tested positive having the target disorder? Is this probability dependent on the prevalence of the target disorder? These are the questions addressed in the present paper. The classical concepts of sensitivity and specificity are presented as well as the more modern and clinically relevant concepts of the predictive values of a positive and a negative test. The author employs different didactic methods such as 2 x 2 tables, graphical illustrations and natural frequencies for elaborating on these often intermixed concepts in a clear and easily understandable way.