This presentation is part of: Poster Session - Public Health; Methodological Advances
USING LATENT CLASS ANALYSIS TO ESTIMATE TEST ACCURACY FOR COMMON MEASURES OF CARPAL TUNNEL SYNDROME
Andrew Scott LaJoie, PhD, MSPH, School of Public Health and Information Sciences, University of Louisville, Department of Health Knowledge and Cognitive Sciences, Louisville, KY, Steven J. McCabe, MD, MSc, School of Public Health and Information Sciences, University of Louisville, Department of Psychological and Brain Sciences, Louisville, KY, and Stephen E. Edgell, PhD, University of Louisville, Psychological and Brain Sciences, Louisville, KY.
Purpose The accuracy of a diagnostic test used to classify a patient as being diseased or disease-free is a valuable piece of information to be used by the physician when making treatment decisions. If a gold standard reference test is available, determining the sensitivity and specificity of a new test is straightforward. However, if that reference test is incorrectly assumed to be perfectly sensitive and specific, the errors of the reference test can result in an under-estimation of the accuracy of the test being evaluated. Latent class analysis, a technique that uses maximum likelihood estimation, can be applied to determine the sensitivity and specificity of a new test when no gold standard exists. Methods In this study, latent class analysis was used to determine the accuracy rates of three commonly used measures of carpal tunnel syndrome: the Tinel’s Sign, the Phalen’s test, and the nerve-conduction velocity test. Results It was found that the Tinel’s Sign and the Phalen’s test are both highly sensitive, .97 and .92 respectively and specific .91 and .88 respectively. Conclusions The estimates of the sensitivity and specificity of these common tests for carpal tunnel syndrome support their widespread clinical use.
