Skip to main content

Table 1 Study characteristics

From: An updated systematic review of radiomics in osteosarcoma: utilizing CLAIM to adapt the increasing trend of deep learning application in radiomics

Study Characteristics Data
Sample size, mean ± standard deviation, median (range) 86.6 ± 45.8, 81 (17–191)
Journal type, n (%) N = 29
 Imaging 13 (44.8)
 Non-imaging 16 (55.2)
First authorship, n (%) N = 29
 Radiologist 19 (65.5)
 Non-radiologist 10 (34.5)
Imaging modality, n (%) N = 29
 CT 9 (31.0)
 MRI 14 (48.3)
 PET 6 (20.7)
Biomarker, n (%) N = 33
 Diagnostic 3 (9.1)
 Predictive 18 (54.5)
 Prognostic 12 (36.4)
Model type, n (%) N = 33
 Type 1a: Developed model validated with exactly the same data 8 (24.2)
 Type 1b: Developed model validated with resampling data 8 (24.2)
 Type 2a: Developed model validated with randomly splitting data 12 (36.4)
 Type 2b: Developed model validated with non-randomly splitting data 1 (3.0)
 Type 3: Developed model validated with separate data 4 (12.1)
 Type 4: Validation only 0 (0.0)
  1. There were 33 radiomics models identified in 29 included studies. The model type was determined according to criteria in TRIPOD statement. TRIPOD Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis