Seminar

Todd Alonzo

Study Designs to Compare Accuracy of Two Dichotomous Screening Tests With Incomplete Disease Verification

The accuracy (sensitivity and specificity) of a new screening test can be compared with that of a standard test by applying both tests to a group of subjects in which disease status can be determined by a gold standard (GS) test. However, it is not always feasible to administer a GS test to all study subjects. For example, a study is planned to determine if a new screening test for cervical cancer is better than the standard test, and in this setting it is not feasible (or ethical) to determine disease status by biopsy in order to identify women with and without disease for participation in a study. When determination of disease status is not possible for all study subjects, the ratio of the accuracy of two screening tests can still be estimated using a paired screen positive (PSP) design in which all subjects receive both screening tests, but only have the GS test if one of the screening tests is positive. Unfortunately in the cervical cancer example, the PSP design is also infeasible because it is not technically possible to administer both screening tests at the same time. In this talk a randomized paired screen positive (RPSP) design is described in which subjects are randomized to receive one of the two screening tests initially, and only receive the other screening test and gold standard if the first screening test is positive. We derive maximum likelihood estimators and confidence intervals for the relative accuracy of the two screening tests, and assess the small sample behavior of these estimators using simulation studies. Sample size formulae are derived and applied to the cervical cancer screening trial example, and the efficiency of the RPSP design is compared with other designs.

Seminar Date:
November 12, 2008