Abstract:
Objective : To analyze the risk factors associated with the development of rectal neuroendocrine tumors (RNETs) and construct a risk prediction model. Methods: Clinical data were collected from patients who underwent electronic colonoscopy from December 2013 to December 2023 in Chengde City Central Hospital, Hebei Province, and the risk factors that might lead to RNETs were included in the comparison of patients with and without RNETs, and the risk prediction model was constructed by applying binary logistic regression to analyze the relevant risk factors. Results: Among 164 patients, 66 had RNETs and 98 did not. Single factor logistic regression analysis showed that age, fatty liver, anxiety and depression, total cholesterol, triglyceride levels, and carcinoembryonic antigen (CEA) were the influencing factors for the RNETs (p<0.05), and Multi-factor logistic regression analysis showed that age(OR=0.96 , 95%CI 0.92-0.99, p=0.015), anxiety and depression (OR=5.38, 95%CI 1.17-24.78, p=0.031), cholesterol level(OR=1.73 , 95%CI 1.14-2.61, p=0.009), fatty liver(OR=8.25, 95%CI 2.34-29.13, p=0.001), CEA(OR=1.54, 95%CI 1.19-1.99, p<0.001) were independent risk factors for the RNETs (p<0.05). After randomly dividing the participants into training and testing sets in the ratio of 7: 3, the training set is used to construct the risk prediction model, and the testing set is used for internal validation of the model.The model’s discrimination was evaluated using the area under the receiver operating characteristic(ROC) curve (AUC), the AUC of the training set and the testing set were 0.843 and 0.772, respectively, and there was no statistically significant difference (p > 0.05), indicating a good discriminative ability . The calibration curves of the training set and the testing set are basically consistent with the 45° standard curve, suggesting that the model predicted probability and the actual probability are basically consistent. The decision curve analysis(DCA) curves of the training set and testing set showed that the net benefit ratio of clinical decision-making of the model was high within the threshold range of 0.2 to 0.7. Conclusion: Being young, having fatty liver disease, CEA, higher cholesterol levels, anxiety and depression are independent risk factors of RNETs. The ability to construct a nomogram model to predict the occurrence of RNETs in patients based on the above risk factors is strong, and clinical intervention can be considered based on the predicted probability values.
下载:
