Related Experiment Video
Updated: Jul 9, 2026
Development and Validation of a Methodology for Establishing Obese Rat Models with Typical Fatty Pancreas
Published on: November 11, 2025
Development and validation of gallstone disease risk factor identification model: a cross-sectional study in Western
Xiaofeng Jing1,2, Qiang Zhang3,4, Tiecheng Zhang2,5
1Department of Hospital Infection-Control, West China Hospital Sichuan University Jintang Hospital. Jintang First People's Hospital, Chengdu, China.
Background:
Gallstone disease poses a growing public health concern worldwide, yet approaches for its identification remain unclear.
Objective:
This study aimed to establish a risk factor identification model by identifying risk factors for gallstone disease, thereby providing evidence-based support for disease prevention.
Methods:
Health examination data and questionnaire data were analyzed. Continuous and categorical variables were compared using t-test or chi-square test. LASSO regression with 10-fold cross-validation was used for variable selection. Logistic regression and random forest models were constructed in parallel. Data were randomly split into training and validation sets (7:3), and 10-fold cross-validation assessed model stability in training set. Model discrimination, calibration, and clinical utility were evaluated using the AUC, calibration curves, and decision curve analysis (DCA).
Results:
Among the 17,768 subjects, 1,673 comprised the gallstone case group and 16,095 the control group. A random forest model was constructed and demonstrated superior performance to logistic regression, with an AUC of 0.747 (95% CI: 0.724-0.771), specificity of 0.91, sensitivity of 0.86, Brier score of 0.073 and F1 score of 63.41%. Calibration curves showed good consistency between predicted and observed probabilities. DCA confirmed that the random forest model provided higher net benefit across a wide range of clinically relevant thresholds compared with treat-all or treat-none strategies.
Conclusion:
The random forest model demonstrated moderate discriminatory ability and clinical relevance for gallstone disease. Confirmed risk factors include TBA, smoking, diabetes, TG, TP, passive smoking, tea consumption, nutrient intake exercise, etc. Identification and intervention targeting these factors may help reduce the incidence of gallstone disease. But as a cross-sectional study, future prospective cohort studies are needed for external validation to establish a robust prediction model.
