Prediction of Postoperative Survival Nomogram of Colorectal Cancer Patients based on Lymph Node Classification: a Study based on a SEER Population

Background: Lymph node metastases have a significant impact on the stage, treatment, and prognosis of patients with Colorectal cancer. Lymph node metastasis (LNM), log odds of positive lymph nodes (LODDS), and lymph node ratio (LNR) are independent prognostic factors for colon cancer. We are working to explore a more accurate prediction model and compare it with the staging predictions proposed by the American Joint Committee on Cancer (AJCC). Methods: A total of 15,957 patients with colorectal cancer who underwent surgical resection were included in the study, and they were randomly divided into training group (11,169 patients) and validation group (4,788 patients). Univariate Cox analysis, random forest regression analysis and Lasso analysis were performed on the training group. Based on the results of the analysis, the best independent prognostic factors were identified and integrated to construct a nomogram. The concordance index (C-index) and calibration curves were used to evaluate the nomograms of the training group and the validation group. Nomograms were compared to AJCC 8th edition TNM staging system using decision curve analysis (DCA) and area under curve (AUC). Results: N, LODDS, and LNR are independent prognostic factors for colorectal cancer. The C-index of nomogram predicting overall survival (OS) is higher than that of the AJCC 8th edition TNM staging system. Decision curve analysis (DCA) and ROC curve suggested that the nomogram was better than AJCC 8th TNM stage in terms of clinical practicability. Conclusions: We constructed a nomogram of the prognosis of patients with colorectal cancer, which may help clinicians provide individualized treatment.