Identifying target populations for screening or not screening using logic regression.
Abstract
Colorectal cancer remains a significant public health concern despite the fact that effective screening procedures exist and that the disease is treatable when detected at early stages. Numerous risk factors for colon cancer have been identified, but none are very predictive alone. We sought to determine whether there are certain combinations of risk factors that distinguish well between cases and controls, and that could be used to identify subjects at particularly high or low risk of the disease to target screening. Using data from the Seattle site of the Colorectal Cancer Family Registry, we fit logic regression models to combine risk factor information. Logic regression is a methodology that identifies subsets of the population, described by Boolean combinations of binary coded risk factors. This method is well suited to situations in which interactions between many variables result in differences in disease risk. We found that neither the logic regression models nor stepwise logistic regression models fit for comparison resulted in criteria that could be used to direct subjects to screening. However, we believe that our novel statistical approach could be useful in settings where risk factors do discriminate between cases and controls, and illustrate this with a simulated data set.