Purpose: To develop a survival prediction model for primary conjunctival malignant tumors.
Methods: Detailed information on cases diagnosed with primary conjunctival malignant tumors from 2000 to 2019 was collected from SEER database.Subsequently, cases meeting the inclusion criteria were randomly assigned to either the development group (1,216 cases) or validation group (608 cases). Relevant risk factors affecting overall survival (OS) were identified using Cox proportional hazards regression analysis. A nomogram was constructed to predict the 1-year, 3-year, and 5-year survival rates. The concordance index (C index) was calculated to assess the predictive power of the model. Receiver operating characteristic curves (ROC curves) and calibration curves were plotted. The area under the curve (AUC) was measured. Decision curve analysis (DCA) was also applied.
Results: The overall survival rate was 77.8%. Statistically significant differences in the survival time distribution were observed among groups based on age (P < 0.001), histology (P < 0.001), and stage (P = 0.01). According to the multivariate analysis, patients with lymphoma, younger age, and localized lesions exhibited better survival outcomes. The C-index of the constructed model was 0.79. In the training group, the AUC values for predicting 1-year, 3-year, and 5-year mortality were 0.824, 0.796, and 0.815, respectively. In the validation group, tge corresponding AU values were 0.750, 0.820, and 0.838. The DCA results demonstrated a significant advantage of the model, while the calibration plots indicated that the predicted OS was in good agreement with the actual OS in both groups.
Conclusions: This study presents a satisfying survival prediction model for malignant conjunctival tumors.
