Table 4.
Analysis of deviance for various logistic regression models.
| Model Comparison | Res.Df. | Res.Dev. | Df. | Dev. | p-value |
|---|---|---|---|---|---|
| Radiomics + Smoke + ETOH + T | 70 | 56.74 | |||
| Smoke + ETOH + T | 72 | 84.42 | -2 | -27.68 | <0.0001 |
| Radiomics + Smoke | 74 | 60.47 | |||
| Smoke | 76 | 89.33 | -2 | -28.86 | <0.0001 |
| Radiomics + ETOH | 74 | 59.34 | |||
| ETOH | 76 | 90.13 | -2 | -30.79 | <0.0001 |
| Radiomics + T | 72 | 59.24 | |||
| T | 74 | 84.78 | -2 | -25.53 | <0.0001 |
| Radiomics + ETOH + Smoke | 73 | 58.99 | |||
| ETOH + Smoke | 75 | 89.10 | -2 | -30.11 | <0.0001 |
| Radiomics + T + Smoke | 71 | 58.60 | |||
| T + Smoke | 73 | 84.65 | -2 | -26.04 | <0.0001 |
| Radiomics + T + ETOH | 71 | 56.88 | |||
| T + ETOH | 73 | 84.45 | -2 | -27.57 | <0.0001 |
| Radiomics + Smoke + ETOH + T | 70 | 56.74 | |||
| Radiomics | 75 | 61.55 | -5 | -4.81 | 0.4398 |
Comparisons assess the impact of radiomics inclusion. The first tests the superiority of the full model (radiomics and clinical) over the clinical model alone, while the rest evaluates the model with or without radiomics. Significant p-values favor the full model in all comparisons. The table details degrees of freedom (Res.Df.), residual deviance (Res.Dev.), changes in degrees of freedom (Df.), changes in deviance (Dev.), and associated p-values.