Model integrating CT-based radiomics and genomics for survival prediction in esophageal cancer patients receiving definitive chemoradiotherapy

Table 1 Comparison of patients’ characteristics between training and validation groups

Variables		Training group (N = 82)	Validation group (N = 36)	p
Gender	Male	59	28	0.508
	Female	23	8
Age	≤ 65	34	18	0.390
	>65	48	18
KPS	≤ 80	44	15	0.230
	>80	38	21
Smoking status	Never	41	18	1
	Former/current	41	18
Alcohol consumption	Never	52	22	0.812
	Former/current	30	14
Tumor location	Cervical	4	5	0.203
	Upper thoracic	36	11
	Middle thoracic	27	15
	Lower thoracic	15	5
Clinical stage	II	11	7	0.402
	III	71	29
Radiation dose	> 60 Gy	13	3	0.546
	> 50.4 Gy ≤ 60 Gy	52	25
	≤ 50.4 Gy	17	8
Chemoradiotherapy	SCRT	39	21	0.281
	CCRT	43	15
Radiation therapy	3D-CRT	14	7	0.756
	IMRT	68	29
CHEK2	Wild	77	34	1
	Mutation	5	2
NOTCH2	Wild	75	33	1
	Mutation	7	3
HRR pathway status	Wild	70	28	0.312
	Mutation	12	8
Rad-score	≤ 0.36	32	14	0.989
	> 0.36	50	22

Abbreviations: KPS Karnofsky performance status, SCRT sequential chemoradiotherapy, CCRT concurrent chemoradiotherapy; IMRT intensity modulated radiation therapy, 3D-CRT 3-dimensional conformal radiation therapy

ISSN: 2050-7771