Develop and validate a radiomics space-time model to predict the pathological complete response in patients undergoing neoadjuvant treatment of rectal cancer: an artificial intelligence model study based on machine learning

Table 3 Results of univariate and multivariate logistic regression analyses

Variables	Univariate logistic regression		Multivariate logistic regression
Variables	OR (95%CI)	P value	OR (95%CI)	P value
Age	0.984 (0.948, 1.023)	0.597	NA	NA
Sex	1.113 (0.609, 2.034)	0.728	NA	NA
CEA	1 (0.99, 1.009)	0.919	NA	NA
CA199	1.002 (0.999, 1.004)	0.221	NA	NA
DIS	1.335 (1.055, 1.689)	0.016*	1.397 (1.032, 1.891)	0.03*
CRM status	0.564 (0.211, 1.512)	0.255	NA	NA
mrEMVI status	0.673 (0.247, 1.838)	0.440	NA	NA
T stage	1.296 (0.248, 6.771)	0.758	NA	NA
N stage	0.956 (0.230, 3.981)	0.951	NA	NA
Combined basic model score	25.861 (6.561, 101.932)	< 0.001	28.554 (6.618, 123.204)	< 0.001*

Note: CEA, carcinoembryonic antigen; CA199, carbohydrate antigen 199; DIS, the distance from the end of the convex edge of the tumor to the edge of the anus; CRM, circumferential resection margin; mrEMVI, MRI-based extramural vascular invasion

ISSN: 1471-2407