Sentiment Analysis for Necessary Preview of 30-Day Mortality in Sepsis Patients and the Control Strategies

Table 4

Univariate and multivariate Cox regression analysis of 30-day mortality.

Variables	Univariate analysis		Multivariate analysis
	HR (95%CI)		HR (95%CI)		β
Sentiment polarity score	0.49 (0.44–0.54)	<0.001	0.58 (0.51–0.67)	<0.001	−0.54
Sentiment subjectivity score	0.80 (0.69–0.93)	0.004	0.82 (0.71–0.94)	0.006	−0.20
SAPS-II	1.03 (1.03–1.03)	<0.001	1.03 (1.02–1.03)	<0.001	0.02
SOFA	1.01 (0.99–1.03)	0.278	1.01 (0.98–1.03)	0.283	0.01
Age (<40), years
40–59	0.72 (0.63–0.82)	<0.001	1.59 (1.15–2.19)	0.005	0.46
60–69	1.18 (1.03–1.35)	0.016	1.96 (1.41–2.72)	<0.001	0.67
70–79	1.54 (1.79–2.11)	0.009	1.55 (1.10–2.20)	0.013	0.44
≥80	1.66 (1.48–1.86)	<0.001	2.1 (1.52–2.90)	<0.001	0.74
Gender (female)
Male	1.08 (0.97–1.20)	0.142	1.09 (0.98–1.22)	0.102	0.09
ICU types (CCU)
CSRU	1.02 (0.76–1.37)	0.902	0.65 (0.45–0.94)	0.021	−0.43
MICU	1.10 (0.99–1.22)	0.091	0.69 (0.54–0.87)	0.002	−0.38
SICU	0.85 (0.75–0.97)	0.019	0.56 (0.43–0.73)	<0.001	−0.58
TSICU	0.89 (0.76–1.04)	0.153	0.52 (0.39–0.68)	<0.001	−0.66

Note. HR: hazard ratio; 95%CI: 95% confidence interval; SAPS-II: simplified acute physiology score II; sequential organ failure assessment; ICU: intensive care unit; CCU: coronary care unit; CSRU: cardiac surgery recovery unit; MICU: medical intensive care unit; SICU: surgical intensive care unit; TSICU: trauma/surgical intensive care unit.