BackgroundThe purpose of this study was to construct a clinical prognostic model of primary rectal adenocarcinoma (RAC) to assist in clinical diagnosis and treatment. MethodsPrimary RAC patients from 2010 to 2015 were selected from the surveillance, epidemiology and end results (SEER). The relevant significant variables were used to develop the prognosis model. A score was determined for each prognostic factor in the model. The Kaplan–Meier method and the log-rank test were used to establish and distinguish the survival curves. The accuracy of predictive model was assessed by receiver operating characteristics (ROCs) curve, concordance index (C-index), and decision curve analysis (DCA). ResultsA total of 8069 primary RAC were retrieved in this study. The overall survival(OS)model was established based on 14 variables. The CSS nomogram were constructed using 12 variables. The C-indexes for the training set of OS and CSS were 0.769 (95% confidence interval (CI) 0.761–0.777) and 0.793 (95% CI 0.784–0.802) respectively. The C-indexes for the validation set of OS and CSS were 0.776 (95% CI 0.768–0.784) and 0.794 (95% CI 0.785–0.803) respectively. High-quality calibration plots were observed and the model displayed a favorable outcome compared with (TNM) stage and SEER stage of primary RAC based on DCA curve. We then divided the patients into low-risk, medium-risk, and high-risk groups, showing that patients with primary RAC in the high-risk group had a poor prognosis. A primary RAC prognosis prediction model has been shown by a predicted nomogram for 3 or 5 years and a real-time web-based calculator. ConclusionsIn conclusion, we established a clinical prognosis model for primary RAC for the first time based on a variety of risk factors including individual differences, tumor-related factors, and diagnostic and therapeutic factors, which is more effective than TNM stage in predicting the prognosis of patients. The clinical prediction model visualized by the nomogram for 3 and 5 years and the web-based real-time calculator are helpful to optimize clinical work, facilitate patient consultation and clinical individualized treatment.