Construction and validation of a risk nomogram model for colorectal sessile serrated lesions.

Abstract

ObjectiveThis study aimed to explore the risk factors for colorectal sessile serrated lesions and construct a risk nomogram model.MethodsPatients were enrolled retrospectively from the Affiliated Xuzhou Municipal Hospital of Xuzhou Medical University from January 2019 to September 2023 and randomized to the training and validation sets at a ratio of 7:3. The predictors for constructing the nomogram model were screened via univariate analysis and multivariate logistic regression analysis. Subsequently, the performance of the model was evaluated.ResultsMultivariate logistic regression analysis revealed that age, history of smoking, history of alcohol consumption, and triglyceride-glucose index were independent risk factors for colorectal sessile serrated lesions (p < 0.05). The area under the curve values of the nomogram model in the training and validation sets were 0.715 (95% confidence interval: 0.676-0.753) and 0.742 (95% confidence interval: 0.669-0.815), respectively. The calibration curves showed good homogeneity between the predicted and actual values. Decision curve analysis showed that this nomogram model can achieve positive clinical benefits.ConclusionsAge, history of smoking, history of alcohol consumption, and triglyceride-glucose index are independent predictors of colorectal sessile serrated lesions. This nomogram model may predict the risk of colorectal sessile serrated lesions.