Table 1. Main Characteristics of Patients in the Whole Data Sets of Survival Analysis.
| Characteristica | Data set, No. (%) | ||
|---|---|---|---|
| Training | SEER (test 1) | CHINA (test 2) | |
| Age at diagnosis, median (range), y | 68 (28-95) | 68 (19-92) | 60 (30-87) |
| Sex | |||
| Female | 6657 (51.6) | 1639 (50.8) | 642 (54.3) |
| Male | 6255 (48.4) | 1589 (49.2) | 540 (45.7) |
| Histologic type | |||
| Adenocarcinoma | 8794 (68.1) | 2243 (69.5) | 948 (80.2) |
| Squamous cell carcinoma | 4118 (31.9) | 985 (30.5) | 234 (19.8) |
| Marital status at diagnosis | |||
| Unmarried | 5304 (41.1) | 1843 (57.1) | 526 (44.5) |
| Married | 7608 (58.9) | 1385 (42.9) | 656 (55.5) |
| T | |||
| T1a | 563 (4.4) | 139 (4.3) | 128 (10.8) |
| T1b | 3156 (24.4) | 804 (24.9) | 396 (33.5) |
| T1c | 2342 (18.1) | 641 (19.9) | 346 (29.3) |
| T2a | 3258 (25.2) | 791 (24.5) | 208 (17.6) |
| T2b | 594 (4.6) | 141 (4.4) | 56 (4.7) |
| T3 | 1994 (15.4) | 445 (13.8) | 40 (3.4) |
| T4 | 1005 (7.8) | 267 (8.3) | 8 (0.7) |
| N | |||
| N0 | 9712 (75.2) | 2439 (75.6) | 1030 (87.1) |
| N1 | 1732 (13.4) | 418 (12.9) | 54 (4.6) |
| N2 | 1422 (11) | 356 (11) | 98 (8.3) |
| N3 | 46 (0.4) | 15 (0.5) | 0 |
| M | |||
| M0 | 12 559 (97.3) | 3132 (97) | 1182 (100) |
| M1a | 143 (1.1) | 41 (1.3) | 0 |
| M1b | 202 (1.6) | 52 (1.6) | 0 |
| M1c | 8 (0.1) | 3 (0.1) | 0 |
| LCCS | |||
| Alive | 10 581 (81.9) | 2666 (82.6) | 956 (80.9) |
| Dead | 2331 (18.1) | 562 (17.4) | 226 (19.1) |
| Surgery to primary site | |||
| Pneumonectomy | 613 (4.7) | 132 (4.1) | 40 (3.4) |
| Lobectomy | 10 766 (83.4) | 2695 (83.5) | 872 (73.8) |
| Sublobar | 1444 (11.2) | 369 (11.4) | 270 (22.8) |
| None | 89 (0.7) | 32 (1.0) | 0 |
Abbreviations: LCCS, lung cancer–specific survival; M, metastasis; N, node; SEER, Surveillance, Epidemiology, and End Results cancer registry; T, tumor.
a
Other detailed clinical characteristics can be found in eTables 2 and 3 in the Supplement.