Prognostic Modeling and Treatment Analysis in Primary Central Nervous System Lymphoma: A Retrospective SEER Study

Background: Primary central nervous system lymphoma (PCNSL) is a rare and aggressive malignancy with no established standard of care. Patients with PCNSL have a poor prognosis, and corresponding clinical research is limited. Objective: Using the US SEER database, this study aimed to investigate prognostic factors and construct an individualized prognostic prediction model for PCNSL. Methods: We enrolled 680 patients with PCNSL and randomly divided them into training and validation cohorts. Univariate and multivariate Cox regression analyses were performed to identify independent prognostic factors, which were then used to construct nomogram models for predicting 1-, 2-, and 3-year overall survival. The model's discriminatory ability, accuracy, and clinical utility were evaluated using the concordance index (C-index), area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). Results: Age, chemotherapy, tumor size, and total gross resection (TGR) were identified as independent prognostic factors. The nomogram demonstrated satisfactory predictive performance in both the training and validation cohorts, with C-indices of 0.699 (95% CI, 0.660–0.737) and 0.733 (95% CI, 0.681–0.785), respectively. Survival analysis showed that surgery combined with chemotherapy significantly improved patient prognosis. Conclusion: This study successfully developed and validated an effective prognostic nomogram for PCNSL, providing a practical tool for individualized prognosis assessment. The results support the combination of surgical resection and chemotherapy as a potential treatment strategy for selected patients with PCNSL.