The effect of misclassification of disease status in follow-up studies: implications for selecting disease classification criteria.

For many diseases, a set of diagnostic criteria with perfect sensitivity and specificity does not exist. In the design of a follow-up study of such a disease, one often has a choice between using a set of narrow classification criteria for the disease outcome (i.e., a test with relatively high specificity and relatively low sensitivity) or a broader set of criteria (i.e., a more sensitive, less specific test). A model was investigated which simulated choices one may have between disease classification tests, to determine how the required sample size and bias in the estimates of the risk ratio and risk difference varied between tests. A two-sample study with nondifferential misclassification of disease outcome was assumed. Based on the model, the bias in the risk ratio increases as one increases the sensitivity of the diagnostic test at the expense of specificity. Conversely, the bias in the risk difference decreases with increasing sensitivity and declining specificity. The required sample size is minimized at relatively high sensitivity and relatively low specificity. Selection of the disease classification test as that at which the required sample size is minimized could reduce some of the large data collection costs of follow-up studies. The advantages and limitations of applying this technique to actual studies are discussed.