70
reads

Shang-Ying Shiu

2010-10-08
12:30:00 - 14:30:00

405 , Mathematics Research Center Building (ori. New Math. Bldg.)

Statistical methods for the evaluation of the accuracy of diagnostic tests usually assume a binary true disease status. However, this assumption may not be realistic in practical settings in which "disease" is defined by dichotomizing continuous or ordinal categorical measures. In this talk I will present an analysis of studies in which both the diagnostic test and the reference standard are reported as continuous measures. We propose a semi-parametric model for estimating the sensitivity, specificity and the ROC curve in this setting. Under suitable order restrictions on the mean of the test result variable, fitting is done via two alternative approaches: isotonic regression and the monotone smooth splines. The model provides the basis to assess the effect of varying reference standard threshold on the performance of a diagnostic test. An example to evaluate the ability of the maximal SUV in predicting axillary node involvement in women diagnosed with breast cancer is presented.