Table 5. Results of gene-gene interactions analyzed by MDR.
| Genes and rs numbers | Average testing balanced accuracya (%) | Average cross validation consistencyb | P c |
| TOLLIP (rs5744034) | 57 | 7.4 | 0.09 |
| TOLLIP (rs4963060)*TLR4 (rs6478317) | 61 | 6.4 | 0.01 |
| TOLLIP (rs4963060)*TLR4 (rs6478317)*IRAK1 (rs1059703) | 64 | 8.2 | 0.01 |
a
Average testing balanced accuracy is the accuracy of classification of cases and controls in the testing dataset (one-tenth of the data) calculated as (Sensitivity+Specificity)/2.
b
Average cross validation consistency is the number of times the model was selected as the best model after 10-fold cross-validation runs.
c
Significance of accuracy (empirical p-value based on 1000 permutations).