Table 3 Logistic regression models for the association between the morphological features and EBVNet’s prediction on external datasets.
Features | MultiCenter-STAD | TCGA-STAD | ||||||
|---|---|---|---|---|---|---|---|---|
Univariate | Multivariate | Univariate | Multivariate | |||||
OR | P | OR | P | OR | P | OR | P | |
Tertiary lymphoid structure | 1.50 (1.00, 2.25) | 0.050 | NA | NA | 1.45 (0.80, 2.61) | 0.222 | NA | NA |
Medullary histology | 193.17 (26.49, 1408.74) | <0.001 | 58.73 (7.75, 445.00) | <0.001 | 28.60 (6.23, 131.22) | <0.001 | 9.20 (1.87, 45.22) | 0.006 |
Mucinous differentiation | 0.14 (0.06, 0.33) | <0.001 | 0.30 (0.12, 0.76) | 0.011 | 0.71 (0.32, 1.57) | 0.400 | NA | NA |
Adenoid differentiation | 0.41 (0.27, 0.61) | <0.001 | 0.79 (0.41, 1.53) | 0.492 | 0.43 (0.24, 0.78) | 0.005 | 1.31 (0.53, 3.22) | 0.563 |
Papillary differentiation | 0.17 (0.08, 0.36) | <0.001 | 0.55 (0.22, 1.40) | 0.208 | 0.11 (0.04, 0.33) | <0.001 | 0.17 (0.05, 0.53) | 0.003 |
Signet-ring cell | 0.38 (0.23, 0.63) | <0.001 | 0.42 (0.22, 0.82) | 0.010 | 0.50 (0.18, 1.34) | 0.165 | NA | NA |
Poor differentiation | 7.37 (4.38, 12.40) | <0.001 | 5.17 (2.46, 10.87) | <0.001 | 4.02 (2.12, 7.64) | <0.001 | 2.33 (0.92, 5.90) | 0.075 |
Vacuolar nucleus or recognizable nucleolus | 4.30 (2.82, 6.55) | <0.001 | 1.67 (0.98, 2.84) | 0.059 | 4.11 (2.16, 7.80) | <0.001 | 3.86 (1.87, 7.98) | <0.001 |
