ObjectiveTo investigate the value of predictive models established based on machine learning methods in predicting the risk of metabolic associated fatty liver disease （MAFLD）， and to analyze its key risk factors. MethodsA retrospective analysis was performed for the 50 variables of 2 168 healthy individuals who underwent physical examination in Department of Health Assessment， Xiyuan Hospital， China Academy of Chinese Medical Sciences， from January 2021 to December 2024， including body composition， past history， and laboratory tests， and according to whether they were diagnosed with MAFLD or not， they were divided into MAFLD group with 265 individuals and non-MAFLD group with 1 903 individuals. The Mann-Whitney U test was used for comparison of continuous data between two groups， and the chi-square test was used for comparison of categorical data between two groups. Randomly split the research data into a training set and a validation set in a 70% to 30% ratio. Predictive factors were screened from the training set data using univariate analysis， LASSO regression， and multivariate Logistic regression analysis. Predictive models were then constructed using seven machine learning methods： Logistic regression， decision tree， random forest （RF）， eXtreme gradient boosting， light gradient boosting machine， support vector machine， and artificial neural network. Model performance was evaluated by plotting receiver operating characteristic curve for the validation set and calculating the area under the curve （AUC）， sensitivity， specificity， and Youden index for each model. Furthermore， the SHapley Additive exPlanation （SHAP） method was used to analyze the contribution of variables in the optimal model. ResultsThe prevalence rate of MAFLD among the 2 168 subjects was 12.22% （265/2 168）. Smoking， diastolic blood pressure， phase angle， visceral fat area， muscle fat ratio， waist-to-hip ratio， aspartate aminotransferase， non-HDL-C/HDL-C ratio， triglyceride-glucose index， and gallstones were independent risk factors for MAFLD （all P<0.05）. The seven predictive models of support vector machine， eXtreme gradient boosting， decision tree， light gradient boosting machine， artificial neural network， RF， and Logistic regression had an AUC of 0.738， 0.754， 0.757， 0.786， 0.795， 0.796， and 0.815， respectively， in the validation set， among which the RF model had the best discriminatory ability （AUC=0.796， 95% confidence interval： 0.754 — 0.839）， with a sensitivity of 81.01%， a specificity of 63.16%， and a Youden index of 44.17%. The SHAP analysis showed that visceral fat area， waist-to-hip ratio， and diastolic blood pressure were the top three predictive factors in terms of importance. ConclusionThe RF model， constructed based on body composition and clinical indicators， has a good performance in predicting the risk of MAFLD， and its interpretability can help to identify high-risk individuals in the early stage in clinical practice.

Obesity is a chronic low-grade inflammation and a risk factor for diseases such as diabetes， hypertension， dyslipidemia， and malignant tumors， demonstrating an increasingly grim development situation. The nuclear factor-kappa B （NF-κB） signaling pathway is a key signaling pathway involved in the immune response and inflammatory response. In obese individuals， the expression of NF-κB is overactivated， which leads to abnormal inflammatory responses in the body. Therefore， it is expected to alleviate inflammation and treat obesity by regulating the NF-κB signaling pathway， which has been proven effective by a large number of studies. The available studies on the NF-κB signaling pathway mostly focus on tumors， and there is no systematic review of the mechanism of this pathway in mediating obesity and the traditional Chinese medicine （TCM） treatment. We reviewed the research progress in the pathological and physiological processes of obesity mediated by NF-κB signaling pathway and TCM treatment， aiming to give insights into the clinical treatment of obesity with TCM and provide reference targets and research directions for exploring the biological foundations and the development of new TCM preparations.

Objective: To compare the value of a body shape index (ABSI) and body roundness index (BRI) in predicting non-alcoholic fatty liver disease (NAFLD) among non-obese population, so as to provide a reference for the early identification of populations at high risk of NAFLD. Methods: Adults with a body mass index (BMI) of less than 28 kg/m2 who underwent health check-ups in Xiyuan Hospital of China Academy of Chinese Medical Sciences from 2022 to 2024 were selected as the study subjects. Demographic information, disease history, height, weight, waist circumference, blood pressure, and blood lipid indicators were collected, and ABSI and BRI were calculated. NAFLD was diagnosed using abdominal ultrasound. A multivariable logistic regression model was employed to analyze the relationships between ABSI, BRI and NAFLD among non-obese population. A generalized additive model combined with the penalized spline method was used to fit smooth curves to identify nonlinear relationships, and threshold effects were utilized to determine inflection points. The values of ABSI and BRI in predicting NAFLD among non-obese population were used the receiver operating characteristic (ROC) curve. Results: A total of 1 195 individuals were surveyed, including 345 males (28.87%) and 850 females (71.13%). A total of 348 cases of NAFLD were detected among the non-obese population, with a detection rate of 29.12%. The adjusted ABSI (sABSI) in the NAFLD group and non-NAFLD group were 7.95±0.33 and 8.08±0.34, while the BRI were 3.35±0.79 and 4.15±0.64, respectively, with statistically significant differences between the two groups (both P<0.05). Multivariable logistic regression analysis showed that, after adjusting for demographic information, disease history, blood pressure, and blood lipid indicators, both sABSI (OR=1.932, 95%CI: 1.184-3.158) and BRI (OR=1.594, 95%CI: 1.071-2.360) were significantly associated with NAFLD among non-obese population. Nonlinear positive correlations were observed between sABSI, BRI, and NAFLD among non-obese population. When sABSI≤8.46 and BRI≥2.72, both indices were positively associated with NAFLD. The area under the ROC curve for ABSI and BRI in predicting NAFLD risk among non-obese population were 0.619 and 0.782, respectively, with optimal cut-off values of 0.082 and 3.656, respectively. Conclusions ABSI and BRI show a non-linear relationship with NAFLD among non-obese population. BRI demonstrates relatively better performance in predicting NAFLD risk among this population and can serve as an auxiliary indicator for the early identification of NAFLD among non-obese population.