exploratory vs. confirmatory studies
Explorative vs. confirmatory studies in the field of diagnostic studies
Exploratory diagnostic study
Goal: Estimation of diagnostic quality with confidence interval
Advantage of the design: fewer cases.
Disadvantage: no verification.
Should models be developed, e.g. For example, if combinations of several markers are linked to form a mathematical marker, the first study for this is always an exploratory study. The result must be validated in an independent study.
Confirmatory diagnostic study
Goal: Evidence that diagnostic quality is achieved.
The iFOBT test for screening for colon carcinoma is an example of the type of evidence required by the authorities. Here the German authorities (GBA) require a sensitivity of 25% and a specificity of 90%.
Example: Proof that sensitivity is better than 60% and specificity better than 90%. One of the two theses is often formulated as a non-inferiority test: proof that sensitivity is better than 60% and that specificity is not less than 90% relevant.
Two joint null hypotheses are tested, one for sensitivity and one for specificity. Both null hypotheses must be rejected in order to achieve the study goal. As a result, a higher power than usual must be used when calculating the number of cases. If the overall power is set at 80%, the power must be set at just under 90% for each individual test (0.9 x 0.9 ~ 0.8).
Advantage: verification.
Disadvantage of these designs: higher number of cases
