Application of the predictive value model in the analysis of test effectiveness

Abstract

There are four levels at which laboratory tests and procedures can be evaluated relative to their effectiveness: 1. Analytical analysis of laboratory test: precision, accuracy, analytical sensitivity, and analytical specificity. 2. Diagnostic analysis of laboratory test: diagnostic sensitivity, diagnostic specificity, Youden index, likelihood ratio, and ROC curve. 3. Operational analysis of laboratory test: predictive value of positive result, predictive value of negative result, efficiency, discriminant function, and so forth. 4. Medical decision-making analysis of laboratory test: threshold probability, cost-benefit analysis, and solving the decision tree. Laboratory test selection can occur at any level, without knowledge of the test's evaluation and performance at the other levels. Alternatively, the development of new laboratory tests can proceed from level 1 to level 4, or vice versa. Unfortunately, the former is usually the case and most of the tests in use today have never been evaluated at the medical decision-making level. In evaluating clinical laboratory tests, it is essential that the laboratory have at its disposal simple ways to analyze sets of data. The predictive value model has proven to be effective in designing test strategies and evaluating the usefulness of laboratory tests. The widespread use of computers in laboratory medicine should permit this approach to data analysis to become routine in the next few years.