Department of Statistics Seminar
North Carolina State University

presents

Dr. Paul S. Albert

National Cancer Institute

"Latent Class Modeling Approaches for Assessing Diagnostic Error Without a Gold Standard: Applications to p53 Immunohistochemical Assay in Bladder Tumors"

ABSTRACT

Improved characterization of tumors for purposes of guiding treatment decisions for cancer patients will require that accurate and reproducible assay be developed for a variety of tumor markers. No gold standard exist for most tumor marker assay. Therefore, estimates of assay sensitivity and specificity cannot be obtained unless a latent model-based approach is used. Our goal in this talk is to estimate sensitivity and specificity for p53 immunohistochemical assay of bladder tumors using data from a reproducibility study conducted by the National Cancer Institute Bladder Tumor Marker Network. We review latent class modeling approaches proposed by previous authors, and we find that many of these approaches impose assumptions about specimen heterogeneity that are not consistent with the biology of bladder tumors. We present flexible mixture models alternatives that are biologically plausible for our example, and we use them to estimate sensitivity and specificity for our p53 example. These mixture models are shown to offer an improvement over other methods in a variety of settings, but we caution that, in general, care must be taken in applying latent class models. This work is joint with Lisa McShane of NCI and Joanna Shih of NHLBI.

Friday, October 27, 2000

3:35 - 4:35 pm

206 Cox Hall

Refreshments will be served on the second floor of Dabney Hall (left of Room 222) at 3:00 pm.