An application of conditional logistic regression and multifactor dimensionality reduction for detecting gene-gene interactions on risk of myocardial infarction: the importance of model validation

Abstract

Background: To examine interactions among the angiotensin converting enzyme (ACE) insertion/deletion, plasminogen activator inhibitor-1 (PAI-1) 4G/5G, and tissue plasminogen activator (t-PA) insertion/deletion gene polymorphisms on risk of myocardial infarction using data from 343 matched case-control pairs from the Physicians Health Study. We examined the data using both conditional logistic regression and the multifactor dimensionality reduction (MDR) method. One advantage of the MDR method is that it provides an internal prediction error for validation. We summarize our use of this internal prediction error for model validation.

Results: The overall results for the two methods were consistent, with both suggesting an interaction between the ACE I/D and PAI-1 4G/5G polymorphisms. However, using ten-fold cross validation, the 46% prediction error for the final MDR model was not significantly lower than that expected by chance.

Conclusions: The significant interaction initially observed does not validate and may represent a type I error. As data-driven analytic methods continue to be developed and used to examine complex genetic interactions, it will become increasingly important to stress model validation in order to ensure that significant effects represent true relationships rather than chance findings.

Figure 1

Summary of the steps involved in implementing the MDR method.

Figure 2

Summary of two-locus ACE I/D and PAI-1 4G/5G genotype combinations associated with high risk and low risk for myocardial infarction from MDR analysis with the lowest prediction error. For each genotype combination, the number of cases is displayed in the left bar while the number of controls is displayed in the right-box. Darker shade indicates the high risk group. Note that the pattern of high and low risk for the ACE polymorphism differs depending on the value of the PAI-1 polymorphism. This is evidence of epistasis or gene-gene interaction.

Figure 3

Summary of two-locus ACE I/D and PAI-1 4G/5G genotype combinations in the independent validation sample. Darker shade indicates those combinations that were classified as high-risk in the original analysis while lighter shade indicates those combinations that were classified as low-risk in the original analysis. Note that each genotype combination contains a nearly even split of cases and controls. Hence the significant interaction observed in the initial dataset does not appear to validate.