Development and testing of a random forest-based machine learning model for predicting events among breast cancer patients with a poor response to neoadjuvant chemotherapy

Table 2 Cox regression of the patients’ cohort using univariate and multivariate analysis

	Univariate analysis			Multivariate analysis
	P-value	Hazard ratio	95% CI	P-value	Hazard ratio	95% CI
Age (≤ 60 vs. > 60)	0.795	1.088	0.576–2.054
Histological type (Invasive tumor vs. other type)	0.083	0.524	0.253–1.088
T (T1 + T2 vs. T3)	0.048	0.595	0.355–0.995	0.138	0.817	0.626–1.067
N (N0 + N1 vs. N2 + N3)	0.167	0.704	0.428–1.158
HR (negative vs. positive)	< 0.001	2.298	1.485–3.557	0.008	1.373	1.087–1.733
HER2				0.024
Negative vs. positive	0.248	0.678	0.351–1.31	0.67	0.864	0.44–1.694
Llow expression vs. positive	< 0.001	0.427	0.266–0.687	0.008	0.504	0.304–0.835
Ki67 (≤ 20 vs. > 20)	0.162	0.733	0.475–1.133
P53 (negative vs. positive)	0.049	0.602	0.363–0.998	0.025	0.743	0.574–0.963

ISSN: 2047-783X