Development and validation of a novel lymph node classification-based model for predicting survival in major salivary gland cancer

Abstract

Background Current lymph node (LN) staging is controversial in predicting the survival of major salivary gland cancer (MSGC). Recently, a novel LN staging system for MSGC has been proposed. This study aimed to validate the prognostic value of the novel LN staging system and develop a new LN classification-based nomogram to predict the individualized overall survival (OS) of MSGC patients. Methods A total of 4563 MSGC patients were identified from the Surveillance Epidemiology and End Results (SEER) database (2004–2015). They were further randomly divided into the training and validation cohorts (7:3). OS was estimated by the Kaplan-Meier method, and prognostic factors were assessed using Cox proportional hazards model. Then, a prognostic nomogram predicting the survival of SGC was derived and validated. Finally, the discrimination and calibration of the nomogram were evaluated using C-index, the area under the time-dependent receiver operating characteristic curve (time-dependent AUC), and calibration plots. Decision curve analysis (DCA) was used to compare the clinical practicability between the nomogram and American Joint Committee on Cancer (AJCC) staging system. Results The novel LN staging system was found to be independently associated with OS in MSGC, and it exhibited better discriminatory ability than the current AJCC LN staging system. Meanwhile, a prognostic nomogram based on this staging was formulated. The C-index of the nomogram was 0.793 (95% CI: 0.781–0.805) in the training cohort, which was higher than the C-index of the AJCC staging system (0.707, 95% CI: 0.693–0.721, p < 0.001). And the time-dependent AUC (> 0.8) also indicated that the nomogram had a satisfactory discriminative ability. The calibration plots showed that the nomogram predicted was consistent with the actual observation. Additionally, DCA demonstrated that the nomogram had a better clinical application value than the AJCC staging system. Conclusions The novel SGC-specific LN staging system exhibited an excellent prognostic value for OS in patients with MSGC. And the proposed nomogram based on this LN staging showed better accuracy and applicability in predicting the OS of MSGC patients than the AJCC staging system.