Aim:Primary spinal cord lymphoma (PSCL) is an infrequent disorder and has therefore received scant focus. Consequently, neither the usual intervention protocol nor the predictive variables for PSCL were well developed. This study was designed to identify predictive factors associated with the survival of patients with PSCL. Material and Methods:The Surveillance, Epidemiology, and End Results database was used in this study, which involved 254 patients with PSCL. Data on the patients’ age, sex, race, pathology, Ann Arbor stage, adjuvant therapy, and year of diagnosis were collected. Univariate and multivariate Cox regression models were conducted to detect the predictive variables.Results:Of the 254 patients, 67 (26.4%) die from lymphoma at the time of data collection. Cancer-specific survival at 1, 3, and 5 years was 81.0%, 74.6%, and 74.1%, respectively. Diffuse large B-cell lymphoma (DLBL) was the highest prevalent histotype (n = 140, 55.1%). The multivariate Cox regression models revealed that chemotherapy (hazard ratio (HR): 0.47; 95% confidence interval (CI), 0.16–0.82; p = 0.040) and radiochemotherapy (HR: 0.43; 95% CI, 0.10–0.57; p = 0.045) were independent predictors of favorable cancer-specific survival, whereas age ≥ 80 years (HR: 6.51; 95% CI, 1.65–25.64; p = 0.003) and DLBL (HR:1.71; 95% CI, 1.02–2.88; p = 0.030) were independently associated with poor cancer-specific survival.Conclusion:The survival outcome of PSCL is favorable in the current treatment strategy. Chemotherapy and radiochemotherapy were predictors of favorable survival, whereas elderly age and DLBL were associated with poor prognosis.