Establishment of a nomogram model for predicting the prognosis of craniopharyngioma based on SEER database

Objective To analyze the prognostic factors of patients with craniopharyngioma based on the Surveillance, Epidemiology, and End Results (SEER) database. Methods Clinical data were collected from patients who were diagnosed with craniopharyngioma between 2000 and 2019 from SEER database. The overall survival curves were plotted using the Kaplan-Meier method and significance was determined by Log rank test. Univariate and multivariate regression analyses were performed using the Cox proportional hazards model to identify potential predictors. Based on those factors, a nomogram model was established to predict 1-year, 2-year, 5-year and 10-year survival rates of craniopharyngiomas patients. The prediction efficiency was evaluated by the concordance index (C-index), receiver operating characteristic (ROC) curve, area under the curve (AUC) and calibration plots. Results The nomogram model was established through multivariate analysis using the training set. The C-index value of the nomogram model was 0.77 for the training set and 0.75 for the validation set. According to the training and validation sets, the AUC of 1-year, 2-year, 5-year and 10-year survival rates were greater than 0.75. The calibration curves also showed satisfactory consistency between predicted survival and observed outcomes. The areas under the ROC curve of the external verification group for 1 year and 2 years were 0.942 and 0.838. Therefore, the established nomogram model had good predictive effect. Conclusions The influencing factors for the prognosis of craniopharyngioma patients include radiotherapy, tumor size, age, race, marriage and family incomes. The resultant nomogram model has reliable discrimination and accuracy, and is important for prediction prognosis of craniopharyngioma patients.