Study characteristics | Data |
---|---|
Sample size, mean ± standard deviation, median (range) | 137.5 ± 85.0, 111 (41–389) |
Journal type, n (%) | N = 30 |
 Imaging | 16 (53) |
 Non-imaging | 14 (47) |
First authorship, n (%) | N = 30 |
 Radiologist | 24 (80) |
 Non-radiologist | 6 (20) |
Biomarker, n (%) | N = 30 |
 Diagnostic | 24 (80) |
 Prognostic | 6 (20) |
Imaging modality, n (%) | N = 30 |
 CT | 13 (43) |
 EUS | 4 (13) |
 MRI | 9 (30) |
 PET | 4 (13) |
Model type, n (%) | N = 30 |
 Type 1a: Developed model validated with exactly the same data | 7 (23) |
 Type 1b: Developed model validated with resampling data | 10 (33) |
 Type 2a: Developed model validated with randomly splitting data | 12 (40) |
 Type 2b: Developed model validated with non-randomly splitting data | 1 (3) |
 Type 3: Developed model validated with separate data | 0 (0) |
 Type 4: Validation only | 0 (0) |
Phase classification, n (%) | N = 30 |
 Phase 0: < 100 patients; retrospective; internal validation | 16 (53) |
 Phase I: < 100 patients; retrospective; external validation | 2 (7) |
 Phase II: > 100 patients; retrospective; external validation | 12 (40) |
 Phase III: > 100 patients; prospective; external validation | 0 (0) |
 Phase IV: real-world | 0 (0) |