Improving detection of impacted animal bones on lateral neck radiograph using a deep learning artificial intelligence algorithm

Insights into Imaging

Table 1 Demographic data of patients included in the training, validation, testing, and simulation datasets

	Training set	Validation set	Testing set	Simulation set	p
Number of patients	1213	520	100	126
Age (year)	56.27 ± 16.87	55.12 ± 18.56	47.44 ± 23.06	45.18 ± 23.93	< 0.001*
Sex (M, F)	484, 729	208, 312	41, 59	61, 65	0.319
Manufacturer/model
CARESTREAM/DRX-evolution	610	294	71	58
SHIMADZU/RADspeed Pro	15	8	1	42
TOSHIBA/KXO-80G	588	218	28	0