Background: Intracerebral hemorrhage (ICH) is the most fatal subtype of stroke. Despite limited effective therapy, there is no accepted clinical grading scale to predict in- hospital mortality, especially in developing nations. The purpose of this study was to assess the predictors of in- hospital mortality among a sample of Iranian patients with spontaneous ICH for use at the time of the first evaluation.Methods: This prospective study was carried from January 2010 to the end of January 2011. Demographic, clinical, and laboratory data of ICH patients were collected. Hematoma volume and perihematoma edema (PHE) were measured on brain computed tomography scan using ABC/2 formula. Logistic regression analysis was performed to determine independent variables contributing to in- hospital mortality.Results: Of a total 167 consecutive ICH patients, 98 patients met inclusion criteria. Mean ± standard deviation age of patients was 70.16 ± 12.52. Afte multivariate analysis, five variables remained as independent predictors of in-hospital mortality included: age [odds ratio (OR) = 1.12, 95% confidence interval (CI) = 1.03-1.23, P = 0.009], diabetes mellitus (OR = 10.86, 95% CI = 1.08- 109.24, P = 0.009), National Institutes of Health Stroke Scale (NIHSS) score (OR = 1.41, 95% CI = 1.08-1.68, P ≤ 0.001), as well as volume of hematoma (OR = 1.1, 95% CI = 1.03-1.17, P = 0.003), and PHE (OR = 0.75, 95% CI = 0.60-0.93, P = 0.010).Conclusion: Our results indicate that older age, diabetes mellitus, higher NIHSS, as well as larger volume of hematoma, and smaller PHE on admission are important predictors of in-hospital mortality in our ICH patients.