Table 1. Characteristics of the training and validation cohorts.
| Characteristic | Training cohort (n = 30339) | Validation cohort (n = 12991) | ||
|---|---|---|---|---|
| No. | % | No. | % | |
| Age at diagnosis, years | ||||
| Median ± SD | 36 ± 20.0 | 36 ± 20.1 | ||
| Range | 2 - 99 | 1 - 98 | ||
| Gender | ||||
| Male | 16478 | 54.3 | 7044 | 54.2 |
| Female | 13861 | 45.7 | 5947 | 45.8 |
| Race | ||||
| White | 25518 | 84.1 | 10951 | 84.3 |
| Black | 3205 | 10.6 | 1382 | 10.6 |
| Othersa | 1616 | 5.3 | 658 | 5.1 |
| Ann Arbor stage | ||||
| Stage I/II | 18054 | 59.5 | 7734 | 59.5 |
| Stage III/IV | 12285 | 40.5 | 5257 | 40.5 |
| Histological type | ||||
| LR | 1048 | 3.5 | 443 | 3.4 |
| MC | 4536 | 15.0 | 1924 | 14.8 |
| LD | 471 | 1.5 | 209 | 1.6 |
| NS | 18565 | 61.2 | 7924 | 61.0 |
| NOS | 5719 | 18.8 | 2491 | 19.2 |
aOthers includes American Indian/Alaskan Native and Asian/Pacific Islander.
Abbreviations: SD, standard deviation; LR, lymphocyte-rich; MC, mixed cellularity; LD, lymphocyte-depleted; NS, nodular sclerosis; NOS, not otherwise specified.