Stratified models for OS
| Model . | Hazard Ratio (95% CI) . | AIC* . | C-index† (95% CI) . |
|---|---|---|---|
| IPI risk group | 5455 | 0.626 (0.557-0.694) | |
| Low (0-1) | Reference | ||
| Low-intermediate (2) | 1.99 (1.46-2.72) | ||
| High-intermediate (3) | 2.73 (1.99-3.74) | ||
| High (4-5) | 4.51 (3.29-6.16) | ||
| R-IPI risk group | 5492 | 0.590 (0.528-0.652) | |
| Very good (0) | Reference | ||
| Good (1-2) | 1.68 (0.81-3.48) | ||
| Poor (3-5) | 3.67 (1.75-7.67) | ||
| NCCN-IPI risk group | 5428 | 0.632 (0.565-0.700) | |
| Low (0-1) | Reference | ||
| Low-intermediate (2-3) | 1.49 (0.83-2.67) | ||
| High-intermediate (4-5) | 3.95 (2.17-7.19) | ||
| High (6-8) | 6.40 (3.45-11.89) |
| Model . | Hazard Ratio (95% CI) . | AIC* . | C-index† (95% CI) . |
|---|---|---|---|
| IPI risk group | 5455 | 0.626 (0.557-0.694) | |
| Low (0-1) | Reference | ||
| Low-intermediate (2) | 1.99 (1.46-2.72) | ||
| High-intermediate (3) | 2.73 (1.99-3.74) | ||
| High (4-5) | 4.51 (3.29-6.16) | ||
| R-IPI risk group | 5492 | 0.590 (0.528-0.652) | |
| Very good (0) | Reference | ||
| Good (1-2) | 1.68 (0.81-3.48) | ||
| Poor (3-5) | 3.67 (1.75-7.67) | ||
| NCCN-IPI risk group | 5428 | 0.632 (0.565-0.700) | |
| Low (0-1) | Reference | ||
| Low-intermediate (2-3) | 1.49 (0.83-2.67) | ||
| High-intermediate (4-5) | 3.95 (2.17-7.19) | ||
| High (6-8) | 6.40 (3.45-11.89) |
Models were stratified by study and type of induction therapy.
The AIC provided a relative measure of model quality; smaller values correspond with a better fitting model. Differences in AIC <2 between models indicate no improvement in fit, differences >2 but <10 indicate increasing improvement in fit, and differences ≥10 indicate substantial improvement in the fit of the model.
The C-index provided a measure of predictive ability of the model, defined as the probability of concordance between predicted and observed survival. The C-index corresponds to the area under the receiver operating characteristics curve for censored data. C-index values of 0.5, 0.7, and 1.0 indicate that the model has completely random, acceptable, or perfect discrimination, respectively, between short and long survival times.