Clinical and pathological characteristics of and predictive model for colorectal neuroendocrine tumors

Abstract

BackgroundThe incidence of colorectal neuroendocrine tumors (NETs) is increasing, causing a social burden. At present, there is no specific prognostic model for colorectal NETs. Thus, an accurate model is needed to predict the prognosis of patients with colorectal NETs. AimWe aimed to create a new nomogram to predict the prognosis of patients with colorectal NETs. Furthermore, we compared nomogram we established and the 8th edition of the AJCC TNM staging system in terms of prediction ability and accuracy. MethodsA total of 3353 patients with colorectal NETs were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Kaplan-Meier analyses were used to assess overall survival (OS) and cancer-specific survival (CSS). Additionally, LASSO regression was used to select variables for constructing the nomogram. Furthermore, the C-index and time-dependent receiver operating characteristic (tdROC) curve were used to evaluate the nomogram. Decision curve analysis (DCA) was performed to compare the clinical utility of the nomogram with that of the TNM system. An external validation cohort (N = 61) was established to evaluate the nomogram's prediction accuracy. ResultsA total of 9 factors (age, sex, marital status, tumor size, T stage, M stage, N stage, grade, and surgery) were selected based on the results of LASSO analysis. The C-indexes of the nomogram in the training and validation sets were 0.807 and 0.775, respectively, which indicated that the nomogram had better prediction accuracy than TNM staging (C-index = 0.700 in the training set and 0.652 in the validation set). The C-index of the nomogram in the external validation cohort was 0.954, indicating that the nomogram had satisfactory prediction accuracy. The results of DCA revealed that the survival nomogram possessed greater utility in clinical practice. ConclusionWe determined the OS and CSS of patients with colorectal NETs and developed a robust and clinically useful survival nomogram.