Table 3:
Relevance to survival of demographic and disease covariates
| Cases | Events | Terms | Deviance | DF | P |
|---|---|---|---|---|---|
| 101 | 96 | ER | 1.061 | 1 | 0.3029 |
| Then GP88_grp | 7.409 | 3 | 0.0599 | ||
| 101 | 96 | PR | 0.251 | 1 | 0.6162 |
| Then GP88_grp | 7.945 | 3 | 0.0472 | ||
| 101 | 96 | HER2 | 1.177 | 1 | 0.2779 |
| Then GP88_grp | 7.689 | 3 | 0.0529 | ||
| 101 | 96 | Age | 0.008 | 1 | 0.9284 |
| Then GP88_grp | 8.332 | 3 | 0.0396 | ||
| 101 | 96 | Race | 5.777 | 3 | 0.1230 |
| Then GP88_grp | 14.042 | 3 | 0.0028 | ||
| 101 | 96 | Metastases | 7.693 | 1 | 0.0055 |
| Then GP88_grp | 10.801 | 3 | 0.0129 | ||
| 72 | 67 | LNPos | 2.964 | 1 | 0.0851 |
| Then GP88_grp | 6.670 | 3 | 0.0832 | ||
| 69 | 66 | Tumor Size | 2.076 | 1 | 0.1496 |
| Then GP88_grp | 3.755 | 3 | 0.2892 | ||
| 69 | 68 | Tumor Grade | 4.632 | 1 | 0.0314 |
| Then GP88_grp | 3.476 | 3 | 0.3238 |
Covariates were examined to assess their association with survival, and whether GP88 has significant additional information. This was tested by fitting CPH survival models using each predictor followed by the GP88 grouping. The results are provided as the sequential analysis of deviance. For each predictor, the table shows the deviance explained by that predictor and the additional deviance explained by the GP88 group, along with the degrees of freedom (DF) and P value of each. The first two columns show the number of patients and events recorded for each CPH fit. Information for the last three predictors were missing for a substantial fraction of the patients which would explain the paucity of significances for these three later fits.