Construction And Evaluation Of Nomogram Prediction Model For Lymph Node Metastasis In T1-2 Rectal Cancer

Objective:Preoperative accurate prediction of lymph node metastasis is of great significance for the formulation of treatment plans for patients with T1-2 rectal cancer.The objective of this study was to identify the independent risk factors for lymph node metastasis in t1-2 patients with rectal cancer,and to construct a nomogram model that could effectively predict the risk of lymph node metastasis.Methods:A retrospective analysis was performed on the clinical data of 260 patients with stage T1-2 rectal cancer who underwent radical surgery in the The Second Affiliated Hospital of Nanchang University from January 2019 to January 2022.The optimal cutoff value of each continuous variable was determined by receiver operating characteristic(ROC)curve,and the continuous variables were divided into two groups according to the cutoff value.Univariate analysis was used to find out the variables related to lymph node metastasis in patients with T1-2 rectal cancer.Then the importance of related variables was ranked by random forest algorithm,and these variables were included in multivariate Logistic analysis to identify independent risk factors for lymph node metastasis in stage T1-2 rectal cancer.Incorporating independent risk factors into R software to draw a nomogram of a multivariate Logistic regression model.Finally,the performance of the prediction model was evaluated by receiver operating characteristic curve,calibration curve and clinical decision curve.Results:Univariate analysis showed that lymph node metastasis in stage T1-2 rectal cancer was correlated with histological grade,imaging lymph node size,CEA,CA199,SIRI,NLR and FPR(all P < 0.05).There was no significant correlation with gender,age,tumor morphology,tumor size,preoperative AFP,PLR,SII,PNI,MLR,FAR and the distance from tumor to anus(all P > 0.05).The random forest algorithm results showed that the top 5 variables(image lymph node size,histological grade,CEA,CA199 and SIRI)among the variables with meaningful univariate results were exactly the results obtained by the multivariate logistic regression analysis(all P < 0.05).The area under the ROC curve of the nomogram model is 0.829,and the C index and corrected C index are 0.829 and 0.822,respectively.These results show that the model has good predictive ability.Calibration curve and clinical decision curve show that the model has good calibration ability and clinical practicability.Conclusion:The nomogram prediction model constructed by preoperative CEA,CA199,SIRI,imaging lymph node size and histological grade can be an important tool for preoperative assessment of the risk of lymph node metastasis in patients with stage T1-2 rectal cancer.