Table 1. Cohort Characteristics.
| Characteristic | Subset, No. (%) | |||
|---|---|---|---|---|
| Curation Set (n = 1112 Patients) | Reserve Set (n = 1294 Patients) | |||
| Training (n = 884) | Validation (n = 119) | Test (n = 109) | Total | |
| Histologic diagnosis | ||||
| Adenocarcinoma | 658 (74.4) | 84 (70.6) | 78 (71.6) | 968 (74.8) |
| Squamous cell carcinoma | 113 (12.8) | 17 (14.3) | 15 (13.8) | 136 (10.5) |
| Small cell lung cancer | 45 (5.1) | 3 (2.5) | 5 (4.6) | 37 (2.9) |
| Other | 68 (7.7) | 15 (12.6) | 11 (10.1) | 153 (11.8) |
| Disease extent at original diagnosis | ||||
| Early (stage I-III) | 544 (61.5) | 78 (65.5) | 70 (64.2) | NAa |
| Metastatic (stage IV) | 340 (38.5) | 41 (34.5) | 39 (35.8) | NAa |
| Age at genomic sequencing, y | ||||
| <50 | 55 (6.2) | 8 (6.7) | 8 (7.3) | 87 (6.7) |
| 50-59 | 189 (21.4) | 27 (22.7) | 22 (20.2) | 244 (18.9) |
| 60-69 | 301 (34.0) | 42 (35.3) | 39 (35.8) | 442 (34.2) |
| 70-79 | 250 (28.3) | 34 (28.6) | 31 (28.4) | 390 (30.1) |
| ≥80 | 89 (10.1) | 8 (6.7) | 9 (8.3) | 131 (10.1) |
| Sex | ||||
| Male | 359 (40.6) | 51 (42.9) | 47 (43.1) | 521 (40.3) |
| Female | 525 (59.4) | 68 (57.1) | 62 (56.9) | 773 (59.7) |
| Self-reported race | ||||
| White | 795 (89.9) | 106 (89.1) | 94 (86.2) | 1175 (90.8) |
| Asian | 28 (3.2) | 4 (3.4) | 6 (5.5) | 48 (3.7) |
| Black/African American | 30 (3.4) | 1 (0.8) | 6 (5.5) | 39 (3.0) |
| Unknown/declined/other | 31 (3.5) | 8 (6.7) | 3 (2.8) | 32 (2.5) |
Abbreviation: NA, not available.
a
Staging information was not available for reserve set patients, whose records have not been manually reviewed. The other available clinical and demographic data for the reserve set were collected through the Dana-Farber Cancer Institute precision medicine effort (PROFILE).