Skip to main content
. 2024 May 24;73:102656. doi: 10.1016/j.eclinm.2024.102656

Table 1.

Baseline characteristics of patients in the AI model development and evaluation cohort.

Characteristics AI development
External evaluation
P valuea Prospective clinical application evaluation cohort (n = 59)
Overall (n = 870) Training cohort (n = 439) Internal validation cohort (n = 190) External evaluation cohort (n = 241)
Gender, n (%)
 Male 365 (42.0%) 178 (40.5%) 89 (46.8%) 98 (40.7%) 0.303 23 (39%)
 Female 505 (58.0%) 261 (59.5%) 101 (53.2%) 143 (59.3%) 36 (61%)
 Age, years, mean (SD) 55.5 (11.3) 55.7 (11.1) 54.9 (11.0) 55.9 (11.9) 0.617 59.1 (10.5)
 Size, mm, mean (range) 13.7 (5.0–55.0) 13.4 (6.0–50.0) 14.3 (6.0–55.0) 13.5 (5.0–50.0) 0.292 1.4 (7.0–50.0)
Size, n (%)
 ≤20 mm 737 (84.7%) 372 (84.7%) 166 (87.4%) 199 (82.6%) 0.635 46 (78.0%)
 >20 mm 133 (15.3%) 67 (15.3%) 24 (12.4%) 42 (17.4%) 13 (22.0%)
Tumor location, n (%)
 Esophagus 235 (27.0%) 111 (25.3%) 49 (25.8%) 75 (31.1%) 0.582 11 (18.6%)
 Stomach 607 (69.8%) 316 (72.0%) 134 (70.5%) 157 (65.1%) 48 (81.4%)
 Duodenum 9 (1.0%) 4 (0.9%) 3 (1.6%) 2 (0.8%) /
 Colorectum 19 (2.2%) 8 (1.8%) 4 (2.1%) 7 (2.9%) /
Pathological type, n (%)
 GISTs 454 (52.2%) 227 (51.7%) 99 (52.1%) 128 (53.1%) 0.940 29 (49.1%)
 Leiomyomas 416 (47.8%) 212 (48.3%) 91 (47.9%) 113 (46.9%) 28 (47.5%)
 Other / / / / 2 (3.4%)
a

Comparison among the training cohort, the internal validation cohort and the external evaluation cohort.