Table 6.

Patients condition identification results with the second threshold (0.1).

Fold	Network	Correct identified patients	Wrong identified patients	COVID correct identified	Wrong identified as normal	Normal correct identified	Wrong identified as COVID
	Our model	248	7	16	2	232	5
1	Xception	238	17	17	1	221	16
	ResNet50V2	239	16	17	1	222	15
	Our model	254	14	21	2	233	12
2	Xception	234	34	23	0	211	34
	ResNet50V2	245	23	22	1	223	22
	Our model	232	15	17	1	215	14
3	Xception	227	20	18	0	209	20
	ResNet50V2	223	24	17	1	206	23
	Our model	213	7	13	1	200	6
4	Xception	183	37	14	0	169	37
	ResNet50V2	203	17	13	1	190	16
	Our model	222	11	21	1	201	10
5	Xception	212	21	22	0	190	21
	ResNet50V2	216	17	22	0	194	17
	Our model	233.8	10.8	17.6	1.4	216.2	9.4
Avg	Xception	218.8	25.8	18.8	0.2	200	25.6
	ResNet50V2	225.2	19.4	18.2	0.8	207	18.6

The bold values show the maximum value in a column.