Methods and Applications of Statistics in Clinical Trials, Volume 1: Concepts, Principles, Trials, and Designs

Chapter 28

Diagnostic Studies

Carsten Schwenke

28.1 Introduction

Diagnostic studies are performed to investigate the clinical usefulness of a new diagnostic procedure, for example, a new contrast agent for imaging or a new laboratory test to detect antibodies or antigens in blood. Sometimes, these studies are invented to substitute the standard procedure by an improved or less expensive procedure, which is not inferior in terms of efficacy and has some benefit compared with the standard procedure. Before starting a diagnostic study, first the unit for analysis should be defined in the terms “experimental unit” and “observational unit.” All general considerations on clinical studies, as proposed by ICH and other guidelines, apply to diagnostic studies also, but explicit guidelines also exist for diagnostic studies as described in Section 28.2.1 [1,2]. So-called “blinded reader” studies were introduced by these guidelines as part of diagnostic studies to assess the main efficacy objective in the clinical study. The clinical usefulness of a new diagnostic procedure is evaluated using three components: the reliability, the validity, and the add-on value. Reliability and validity are defined components that investigate, along with parameters for measurement and analysis tools, the performance of a diagnostic procedure. To measure the benefit of a new diagnostic procedure for the patient, the add-on value is often shown by an increased validity compared with a control. Throughout this ...