Evolving Interpretation of Screening and Diagnostic Tests in Allergy

Diagnostic tests for allergy usually are performed to confirm a diagnosis of an allergic disease. If a food allergy suspected, a test can help to determine whether it is present, to monitor its activity over time, and to determine whether the allergy is resolving. In this way, tests are used for diagnosis, monitoring, screening, and prognosis. There are 2 schools of thought for using tests: Frequentist and Bayesian approaches. The Frequentist approach defines probability in terms of the frequency of an event if it were to be repeated numerous times and uses parameters such as sensitivity, specificity, and predictive values to make a diagnosis. In contrast, the Bayesian approach defines probability as the degree of belief or disbelief regarding the diagnosis and asserts that only data are real and that test parameters are to be inferred from the data. There are strengths and limitations to each approach; however, the Bayesian approach provides an algorithm leading to a disease probability. To use the Bayesian approach, test results need to be expressed as a likelihood ratio. This helps to determine how much the result of a test changes the probability of a particular diagnosis. Once a probability of disease is determined, decision thresholds need to be defined so that a treatment decision can be made. Using this Bayesian approach, the concept of a false-positive or false-negative test result becomes obsolete. (C) 2021 American Academy of Allergy, Asthma & Immunology