A nomogram for predicting overall survival in patients with endometrial carcinoma: A SEER-based study

ObjectiveTo construct and validate a nomogram for patients with endometrial carcinoma to predict the 3- and 5-year overall survival (OS) based on the Surveillance, Epidemiology, and End Results (SEER) database. MethodsDemographic and clinical pathologic characteristics of patients with endometrial carcinoma diagnosed between 1973 and 2015 were extracted from the SEER database. Univariate and multivariate Cox analyses were carried out to identify the independent characteristics and further included into the construction of a nomogram. Finally, concordance index and calibration curves were used to validate the nomogram. ResultsA total of 49 844 patients were enrolled into our analysis. The results of univariate Cox analysis showed that age, race, marital status, FIGO Stage, grade, and metastatic status to bone, brain, lung, or liver were significant factors. Multivariate Cox analysis was performed and it confirmed all factors as independent variables. Next, a nomogram was constructed using these independent variables in prediction of the 3- and 5-year OS. Furthermore, results with concordance indices (0.852 in training set and 0.861 in validation set) and calibration curves closer to ideal curves indicated the accurate predictive ability of this nomogram. ConclusionsThe individualized nomogram demonstrated a good ability in prognostic prediction for patients with endometrial carcinoma.