Benefits of Dynamic Nomogram Models for Elderly Diffuse Large B-Cell Lymphoma Patients' Early Death Prediction and Clinical Application

BACKGROUND: Diffuse large B-cell lymphoma (DLBCL) is an aggressive malignancy, and about 60% of the patients are diagnosed in their elderly age (≥65 years old). However, little is known about the early mortality and risk factors related to elderly patients with DLBCL. Methodology. From 2000 to 2019, elderly patients diagnosed with DLBCL in the Surveillance, Epidemiology, and End Result (SEER) database were involved in this research and served as test cohort. Moreover, elderly DLBCL patients from Peking University Third Hospital were used for external validation cohort. Risk factors were identified by univariate and multivariate logistic regression analyses. Nomogram models were constructed based on significance risk factors to predict the overall and cancer-specific early death. Besides that, the predictive value of the models was validated by receiver operating characteristic (ROC) analysis. Calibration plots were used to evaluate the calibrating ability. Clinical benefits of nomogram were evaluated by decision curve analysis (DCA). RESULTS: 15242 elderly DLBCL patients obtained from the SEER database and 152 patients from Peking University Third Hospital were enrolled in this research. In the SEER database, 36.6% (5584/15242) of the patients had early death and 30.7% (4680/15242) of them were cancer-specific early death. Marital status, Ann Arbor stage, surgical treatment, radiotherapy, and chemotherapy were significant risk factors for overall and cancer-specific early death of elderly DLBCL patients. Nomograms were constructed according to these risk factors. Then, ROC analysis showed that the AUC of OS was 0.764 (0.756~0.772), and CSS was 0.742 (0.733~0.751). In the validation group, the AUC of OS was 0.767 (0.689~0.846) and CSS was 0.742 (0.743~0.83). CONCLUSION: The calibration plots and DCA analysis revealed that the nomograms were good at early death prediction and clinical application. Predictive dynamic nomogram models for elderly DLBCL patients were established and validated, which might play an essential role in helping physicians enact better treatment strategies.