Randomized trial evaluates predictive values of rules for combining diagnostic tests, suggesting optimizing diagnostic accuracy.
SUMMARY The predictive values of the simple believe-the-positive and believe-the-negative rules for combining two diagnostic tests are considered. These rules do not necessarily have better predictive values than a single test; whether they do depends on the association between test outcomes. Criteria are given, and can be illustrated graphically, to determine when gains in predictive value occur. In general, unless the disease and disease-free test associations are highly asymmetric, the believe-thepositive rule will lead to higher negative and lower positive predictive value. Conversely, the believethe-negative rule will increase the positive and decrease the negative predictive value. However, it is possible that gains in both positive and negative predictive value could arise if test associations are
No takes yet. Share an insight, caveat, or question.
Richard Marshall (1989) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: