Abstract
This paper explores the factors involved in assessing the value of a medical test in a given clinical situation. It examines the problems involved in designing studies to investigate the role for a tumour marker in differential diagnosis and patient monitoring. An overview is given, including a critical evaluation of the preliminary research, the laboratory assay technique and potential clinical problems. Some examples are given. Specific approaches to the analysis of monitoring data are outlined, including the application of a sequential Bayesian model. This is illustrated using data from patients in the Medical Research Council's series of studies on the tumour marker Carcinoembryonic antigen.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have