Understanding and using sensitivity, specificity and predictive values.

Dear Editor,

I have read with interest the article entitled ″Understanding and using sensitivity, specificity and predictive values″ by Parikh et al.1 However, I partially disagree with the authors′ view in the concept of diagnostic test, and subsequently the concept of sensitivity and specificity mentioned through the article. Firstly, the authors mention in the first paragraph ″The basic idea of performing a diagnostic test is to increase (or decrease) our suspicion that a patient has a particular disease″; what they mention is not always the purpose of a diagnostic test, as in some cases what we are looking for is to select a healthy sample from the target population.2 In the second paragraph, the authors stressed on the concept of diagnostic test, which just referred to diseased patients, and they excluded the healthy ones from the definition. Secondly, the true positive and true negative [TP and TN] depends on the point we are interested in, in our research.3 The importance of sensitivity and specificity in any research, when comparing two tests (the new one versus the gold standard) depends on the purpose of the study. Finally, the paper failed to discuss the methods used to calculate both the sensitivity and specificity in the absence of gold standard methods. They also missed to cite in the article Galen et al.4 who invented the method of sensitivity and specificity.