多发结肠息肉的危险因素及风险预测模型的构建与验证OA

Objective To explore the risk factors of multiple colorectal polyps,and to construct and verify the risk prediction model.Methods This retrospective analysis the clinical data of patients with multiple colorectal polyps diagnosed by colonoscopy in Ningbon First Hospital Longshan Hospital Medical and Health Group from September 2021 to April 2024.According to the ratio of 7∶3,the subjects were randomly split into training set and validation set.Univariate and multivariate logistic regression analyses were performed to identify the risk factors associated with the occurrence of multiple colorectal polyps,and a nomogram model was subsequently established using R software to predict the risk of multiple colorectal polyps,the performance of which was evaluated in terms of predictive accuracy,calibration,and clinical utility through the receiver operating characteristic(ROC)curve,the Hosmer-Lemeshow test,and decision curve analysis(DCA).Results totally 408 patients were included in the analysis,of whom 285 were assigned to the training set and 123 to the validation set.Regression analysis showed that age,smoking history and fatty liver were independent risk factors for multiple colorectal polyps.The AUC of the training set and the validation set of the Nomogram model were 0.651(95%CI:0.585-0.717)and 0.749(95%CI:0.657-0.841),respectively.The calibration curve fit was good,and the decision curve analysis demonstrated that the Nomogram model had good clinical practicability.Conclusion The Nomogram model based on age,smoking history and fatty liver has a good predictive value for the risk of multiple colorectal polyps in patients.