. 2024 Mar 14;12:e17098. doi: 10.7717/peerj.17098

Table 2. Baseline data table of train and test tets after sample balancing.

Characteristics	Train set		Pvalue	Test set		P value
	NBM (n = 12, 762)	BM (n = 2, 556)		NBM (n = 5, 477)	BM (n = 1, 089)
Sex, n (%)			0.135			0.776
Male	5,206 (34%)	1,002 (6.5%)		2,188(33.3%)	430 (6.5%)
Femal	7,556 (49.3%)	1,554 (10.1%)		3,289 (50.1%)	659 (10%)
Grade, n (%)			<0.001			<0.001
1	3,172 (20.7%)	255 (1.7%)		1,377 (21%)	103 (1.6%)
2	5,766 (37.6%)	1,237 (8.1%)		2,477 (37.7%)	536 (8.2%)
3	3,747 (24.5%)	1,058 (6.9%)		1,592 (24.2%)	446 (6.8%)
4	77 (0.5%)	6 (0%)		31 (0.5%)	4 (0.1%)
TumorSite, mean ± sd	2.767 ± 1.3611	2.6099 ± 1.3242	<0.001	2.7674 ± 1.3956	2.5849 ± 1.3041	<0.001
TStage, n (%)			<0.001			<0.001
T1	8,740 (57.1%)	1,294 (8.4%)		3,736 (56.9%)	545 (8.3%)
T2	2,152 (14%)	327 (2.1%)		955 (14.5%)	136 (2.1%)
T3	1,136 (7.4%)	497 (3.2%)		451 (6.9%)	229 (3.5%)
T4	734 (4.8%)	438 (2.9%)		335 (5.1%)	179 (2.7%)
NStage, n (%)			<0.001			<0.001
N0	9,524 (62.2%)	696 (4.5%)		4,163 (63.4%)	292 (4.4%)
N1	1,008 (6.6%)	315 (2.1%)		395 (6%)	126 (1.9%)
N2	1,807 (11.8%)	1,247 (8.1%)		722 (11%)	552 (8.4%)
N3	423 (2.8%)	298 (1.9%)		197 (3%)	119 (1.8%)
TumorSize, mean ± sd	19.859 ± 6.3537	22.569 ± 5.854	<0.001	19.625 ± 6.3399	22.017 ± 5.8392	<0.001
Race, n (%)			<0.001			<0.001
White	11,616 (75.8%)	2,308 (15.1%)		4,983 (75.9%)	994 (15.1%)
Black	0 (0%)	98 (0.6%)		0 (0%)	33 (0.5%)
Other	1,146 (7.5%)	150 (1%)		494 (7.5%)	62 (0.9%)
Age, mean ± sd	67.562 ± 10.143	66.028 ± 10.838	<0.001	67.721 ± 10.165	66.185 ± 10.658	<0.001
Marital, n (%)			<0.001			<0.001
Yes	7,112 (46.4%)	1,855 (12.1%)		3,093 (47.1%)	777 (11.8%)
No	5,650 (36.9%)	701 (4.6%)		2,384 (36.3%)	312 (4.8%)

Notes.