Table 5. Baseline logistic regression model and generalized regression Elastic Net model on the predictors of breast cancer from gene-environment interactions.
| Logistic Regression Original Model with Validation | Generalized Regression Elastic Net Model |
|||||
|---|---|---|---|---|---|---|
| With AICc Validation | With Leave-One-Out Validation | |||||
| Parameters | Estimate | p (X2) | Estimate | p (X2) | Estimate | p (X2) |
| (Intercept) | 0.0025 | 0.9986 | -0.2270 | 0.8445 | -0.5199 | 0.5019 |
| BMI * Alcohol | 2.5212 | 0.1176 | 2.8496 | 0.0119 | 2.8879 | 0.0027 |
| BMI * MTR 2756 | -2.3841 | 0.1659 | -1.9493 | 0.1314 | -2.4105 | 0.0090 |
| Alcohol | -1.9568 | 0.1834 | -2.0448 | 0.0306 | -2.1418 | 0.0126 |
| Saturated Fat | 0.6984 | 0.2954 | 0.9178 | 0.0868 | 0.9299 | 0.0868 |
| MTR 2756 | 1.6116 | 0.3091 | 1.1838 | 0.3044 | 1.4942 | 0.1146 |
| MTHFR 1298 * MTRR 66 | 1.1764 | 0.3459 | 1.9493 | 0.0659 | 1.2469 | 0.2189 |
| MTRR 66 | 0.0372 | 0.9675 | -0.7873 | 0.3131 | -0.2323 | 0.7576 |
| MTHFR 1298 | -0.4192 | 0.6226 | -0.3404 | 0.6572 | -0.0551 | 0.9438 |
| BMI | -0.3813 | 0.7847 | -0.2402 | 0.8473 | 0 | 1.0000 |
| Misclassification Rate | 0.3000 | 0.3125 | 0.2785 | |||
| AICc | 70.35 | 117.96 | n/a | |||
| Area under the curve | 0.7240 | 0.7469 | 0.7532 | |||
Note. AICc: Akaike’s information criterion with correction.