The NIHSS score can predict the outcome of patients with primary intracerebral hemorrhage

Table 2 Predictors for overall mortality in the studied cross section (N = 120) by univariate analysis

	β	SE	OR (95% CI)		p value
Midline shift	+ 0.443	0.103	1.557	(1.273–1.903)	< 0.001 (HS)
Mod. edema	+ 1.540	0.734	4.666	(1.108–19.649)	0.036 (S)
IVH	+ 0.197	0.505	7.172	(2.668–19.280)	< 0.001 (HS)
Follow up H. volume	+ 0.079	0.019	1.083	(1.042–1.125)	< 0.001 (HS)
ICH score	+ 2.118	0.421	8.317	(3.647–18.970)	< 0.001 (HS)
NIHSS	+ 0.366	0.070	1.442	(1.258–1.653)	< 0.001 (HS)

Proportional by chance accuracy criteria = 80.7%. The model predicts overall accuracy rate = 84%. Null model − 2 log likelihood = 107.855; full model − 2 log likelihood = 66.203. Overall model chi-square = 41.652, d.f = 13, p < 0.001 (HS) Hosmer and Lemeshow goodness of fit test p = 0.624 (NS), β regression coefficient, SE standard error, OR odds ratio, 95%CI 95% confidence interval. p < 0.05 is significant. p < 0.01 is highly significant