Table 5. Gene–gene interaction models for MALAT1 two polymorphisms for CAD risk by MDR analysis.
| Model | Training Bal. Acc. | Testing Bal. Acc. | Sign Test (P) | CV Consistency | P for permutation test |
|---|---|---|---|---|---|
| Drinking | 0.6598 | 0.6601 | 10 (0.0010) | 10/10 | 0.0000–0.0010 |
| Smoking-Drinking | 0.6790 | 0.6789 | 10 (0.0010) | 10/10 | 0.0000–0.0010 |
| MALAT1 rs4102217-smoking-drinking1 | 0.6995 | 0.6979 | 10 (0.0010) | 10/10 | 0.0000–0.0010 |
| MALAT1 rs4102217-MALAT1 rs619586-smoking-drinking | 0.7054 | 0.6900 | 10 (0.0010) | 10/10 | 0.0000–0.0010 |
The best model was selected as the one with the maximum testing accuracy and maximum CV consistency.
1In this study, the best interaction model was the three-factor model including MALAT1 rs4102217 polymorphism-smoking-drinking.