Skip to main content
. Author manuscript; available in PMC: 2018 Nov 2.
Published in final edited form as: Lab Invest. 2018 Jun 29;98(11):1438–1448. doi: 10.1038/s41374-018-0095-7

Table 3.

Univariate log-rank analysis for overall survival on the test set

Variable Disease-specific survival, HR (95% CI) P value
Age
≤55 vs. >55 1.40 (0.60–3.29) 0.57664
Race
Nonwhite vs. white 0.28 (0.08–0.98) 0.09464
T-stage
T1 vs. T2 1.94 (0.72–5.20) 0.28845
Histology grade
Well/moderately differentiated vs. poorly differentiated 1.74 (0.56–5.39) 0.50248
Histology grade
Well differentiated vs. moderately/poorly differentiated 3.50 (0.74–16.58) 0.23464
Nuclear grade
1 vs. 2/3 1.23 (0.46–3.28) 0.87899
1/2 vs. 3 74.02 (0.80–6854.43) 0.47902
Tubule formation
1 vs. 2/3 1.82 (0.66–5.03) 0.36692
1/2 vs. 3 1.68 (0.37–7.65) 0.77774
Nuclear pleomorphism
1 vs. 2/3 2.29 (0.16–33.57) 0.93666
1/2 vs. 3 0.30 (0.06–1.68) 0.35288
Mitotic count
1 vs. 2/3 74.02 (0.80–6854.43) 0.47902
Her2 status
Positive vs. negative 1.72 (0.65–4.52) 0.39566
Chemotherapy
Yes vs. no 0.55 (0.22–1.40) 0.30872
Image classifier
Positive vs. negative 2.91 (1.23–6.92) 0.02786

CI confidence interval, HR Mantel–Haenszel hazard ratio

Values in bold are statistically significant, p < 0.05