Using Machine Learning to Unravel the Value of Radiographic Features for the Classification of Bone Tumors

Table 2

Patients characteristics: training, validation and test sets.

Characteristics	Binary model		Tertiary model
	Training and validation set	Test set	Training and validation set	Test set
No. of patients	438	189	557	239
Age (y)
ESR
Pathological results
Biopsy benign for bone tumor	298 (68.0)	114 (60.3)	289 (51.9)	123 (51.5)
Biopsy malignant for bone tumor	140 (32.0)	75 (39.7)	150 (26.9)	65 (27.2)
Biopsy intermediate for bone tumor	0	0	118 (21.2)	51 (21.3)

Note: unless otherwise indicated, data are numbers (%) of patient. Data are .