Related Experiment Video
Updated: Aug 10, 2026
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
Development and validation of a predictive model for colorectal polyps in patients with NAFLD based on risk factors
Dong Zhai1, Miaofang Feng2, Xiaojuan Tong3
1The Third Affiliated Hospital of Zhejiang Chinese Medical University (Zhongshan Hospital of Zhejiang Province), Hangzhou, China.
Objective:
Colorectal polyps are precancerous lesions of colorectal cancer. The incidence of colorectal polyps in patients with non-alcoholic fatty liver disease (NAFLD) is significantly higher than that in normal people, but the underlying risk factors for its occurrence are not yet completely clear. The purpose of this study is to establish and validate a risk prediction model for colorectal polyps in NAFLD, in order to conduct early identification and intervention for high-risk populations.
Methods:
We conducted a meta-analysis to identify the eligible studies that met the inclusion and exclusion criteria, and extracted the potential candidate risk factors for colorectal polyps in patients with NAFLD. Subsequently, a retrospective collection was conducted of patients with NAFLD who underwent colonoscopy at Zhejiang Provincial Hospital from 2023 to 2025. These patients were divided into a training set and a validation set in a 7:3 ratio. Based on the candidate risk factors identified from the meta-analysis, predictive factors were determined using LASSO regression and multivariable logistic regression in the training set, and a nomogram was subsequently constructed. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve analysis, and decision curve analysis (DCA).
Results:
The meta-analysis for identifying candidate risk factors included 7,200 patients with NAFLD, of whom 3,686 had colorectal polyps. Through the combined effect size, subgroup and sensitive analysis, 8 risk factors were selected as candidate risk factors. After LASSO regression and multivariable logistic regression in the training set, six predictors were finally determined for model construction: age ≥ 50, male sex, obesity, diabetes, hypertriglyceridemia, and fatty liver type. Our nomogram model demonstrated acceptable calibration and discrimination in both training and validation sets (AUCs: 0.73 and 0.71). The DCA curve indicated that the nomogram provided a potential net benefit in predicting colorectal polyps in patients with NAFLD.
Conclusion:
This predictive model can identify NAFLD patients at risk of colorectal polyps, aiding early intervention and improving prognosis.
