ObjectiveTo investigate whether visceral fat area （VFA） is an independent risk factor for significant liver fibrosis in patients with nonalcoholic fatty liver disease （NAFLD） based on clinical data， and to establish an effective diagnostic model. MethodsA total of 222 NAFLD patients who attended Department of Hepatology， Guangdong Provincial Hospital of Traditional Chinese Medicine， from January 2021 to April 2025 were enrolled， and according to liver stiffness measurement （≥8 kPa or not）， they were divided into significant fibrosis group and non-significant fibrosis group. Propensity score matching （PSM） was performed at a ratio of 1∶1 to balance the baseline data between the two groups. The independent-samples t test or the Mann-Whitney U test was used for comparison of continuous data between two groups； the chi-square test was used for comparison of categorical data between groups. A Spearman correlation analysis was used to determine the correlation of VFA and other indicators with significant liver fibrosis； univariate and multivariate logistic regression analyses were used to identify whether VFA was an independent risk factor for significant liver fibrosis in NAFLD patients， and the receiver operating characteristic （ROC） curve was plotted to assess the predictive performance of related indicators. ResultsA total of 45 patients with significant liver fibrosis and 177 patients without significant liver fibrosis were enrolled， and after PSM， 90 patients （45 pairs） were finally included in analysis. Compared with the non-significant fibrosis group， the significant fibrosis group had significantly higher levels of body mass index （BMI）， fasting blood glucose （FBG）， glycated hemoglobin （HbA1c）， uric acid （UA）， alanine aminotransferase （ALT）， aspartate aminotransferase （AST）， gamma-glutamyl transpeptidase （GGT）， controlled attenuation parameter （CAP）， and VFA， as well as a significantly higher proportion of patients with visceral fat obesity or three or more metabolic risk factors （all P<0.05）. VFA， BMI， AST， and HbA1c were strongly correlated with significant liver fibrosis （all r>0.5， all P <0.05）， and ALT， GGT， UA， FBG， and CAP were significantly positively correlated with significant liver fibrosis （r=0.3　—　0.5， all P<0.05）. VFA （odds ratio ［OR］=1.040， 95% confidence interval ［CI］： 1.018　—　1.062， P<0.05）， FBG （OR=2.372， 95%CI： 1.199　—　4.691， P<0.05）， and AST （OR=1.032， 95%CI： 1.003　—　1.058， P<0.05） were independent risk factors for significant liver fibrosis in NAFLD patients. The new diagnostic model based on VFA， FBG， and AST （with an area under the ROC curve ［AUC］ of 0.907） had a significantly better performance than aspartate aminotransferase-to-platelet ratio index （AUC=0.834）， fibrosis-4 （AUC=0.660）， triglyceride-glucose index （AUC=0.656）， and NAFLD fibrosis score （AUC=0.768） in predicting significant liver fibrosis in NAFLD patients （all P<0.05）. ConclusionVFA is an independent risk factor for significant liver fibrosis in NAFLD patients， and the noninvasive diagnostic model based on VFA， FBG， and AST can effectively predict the onset of significant liver fibrosis in NAFLD patients.

Nutritional support is essential for improving survival and prognosis in critical care medicine.However,traditional nutritional assessment methods have limitations such as strong subjectivity,dependence on clinical experience,lack of real-time data support,especially in complex environments such as intensive care unit(ICU).In recent years,the development of artificial intelligence(AI)technology has provided new opportunities for precise nutrition management.AI can analyze a large amount of clinical data through machine learning algorithms,monitor the physiological state of patients in real time,and dynamically adjust nutritional regimens to optimize the nutritional support effect of critically ill patients.At present,the application of AI in critical nutrition assessment mainly focuses on nutritional risk screening and tolerance assessment,but it is still in the preliminary exploration stage.The application of machine learning,deep learning and data mining technologies in the medical field provides more objective and efficient tools for nutritional assessment,such as personalized intervention by analyzing multi-dimensional data of patients(eating habits,physiological indicators,disease history,etc.).This paper analyzes the research prospect of AI in nutritional support treatment evaluation of critically ill patients,the application status,potential advantages and challenges of AI technology in nutritional assessment,focuses on the application of AI in data analysis,personalized nutrition plan formulation and clinical decision support,and discusses how to improve the effectiveness and safety of nutritional treatment by integrating multiple data sources,thus providing direction and ideas for future research.And through in-depth understanding of the application potential of AI,clinical medical staff can provide more accurate and scientific evaluation basis for nutritional support treatment of critically ill patients,and finally improve the clinical treatment effect of patients.However,widespread adoption of AI still faces challenges such as data privacy,ethical norms,algorithmic bias,and interdisciplinary collaboration.In the future,it is necessary to further optimize algorithm models,strengthen multidisciplinary cooperation(such as the collaboration of clinicians,nutritionists,and data engineers),and solve issues such as data standardization,cost-effectiveness,and patient privacy protection to achieve more accurate and personalized nutrition management strategies,ultimately improving the clinical outcomes of critically ill patients.

Nutritional support is essential for improving survival and prognosis in critical care medicine.However,traditional nutritional assessment methods have limitations such as strong subjectivity,dependence on clinical experience,lack of real-time data support,especially in complex environments such as intensive care unit(ICU).In recent years,the development of artificial intelligence(AI)technology has provided new opportunities for precise nutrition management.AI can analyze a large amount of clinical data through machine learning algorithms,monitor the physiological state of patients in real time,and dynamically adjust nutritional regimens to optimize the nutritional support effect of critically ill patients.At present,the application of AI in critical nutrition assessment mainly focuses on nutritional risk screening and tolerance assessment,but it is still in the preliminary exploration stage.The application of machine learning,deep learning and data mining technologies in the medical field provides more objective and efficient tools for nutritional assessment,such as personalized intervention by analyzing multi-dimensional data of patients(eating habits,physiological indicators,disease history,etc.).This paper analyzes the research prospect of AI in nutritional support treatment evaluation of critically ill patients,the application status,potential advantages and challenges of AI technology in nutritional assessment,focuses on the application of AI in data analysis,personalized nutrition plan formulation and clinical decision support,and discusses how to improve the effectiveness and safety of nutritional treatment by integrating multiple data sources,thus providing direction and ideas for future research.And through in-depth understanding of the application potential of AI,clinical medical staff can provide more accurate and scientific evaluation basis for nutritional support treatment of critically ill patients,and finally improve the clinical treatment effect of patients.However,widespread adoption of AI still faces challenges such as data privacy,ethical norms,algorithmic bias,and interdisciplinary collaboration.In the future,it is necessary to further optimize algorithm models,strengthen multidisciplinary cooperation(such as the collaboration of clinicians,nutritionists,and data engineers),and solve issues such as data standardization,cost-effectiveness,and patient privacy protection to achieve more accurate and personalized nutrition management strategies,ultimately improving the clinical outcomes of critically ill patients.

Repetitive transcranial magnetic stimulation (rTMS) has become an essential method in psychiatric disorders. However, many problems occurred in clinical application. This article interpreted the Association Standard T/CMEAS 011-2023'Operating Specifications for Repetitive Transcranial Magnetic Stimulation in Clinical Applications on Psychiatric Disorders′ released by the Chinese Medicine Education Association. The main content included a range of applications, normative references, terms and definitions, site specifications, equipment specifications, ability specifications of rTMS operators and rTMS process specifications.This article provided suggestions for clinical applications of rTMS on psychiatric disorders.

Repetitive transcranial magnetic stimulation (rTMS) has become an essential method in psychiatric disorders. However, many problems occurred in clinical application. This article interpreted the Association Standard T/CMEAS 011-2023'Operating Specifications for Repetitive Transcranial Magnetic Stimulation in Clinical Applications on Psychiatric Disorders′ released by the Chinese Medicine Education Association. The main content included a range of applications, normative references, terms and definitions, site specifications, equipment specifications, ability specifications of rTMS operators and rTMS process specifications.This article provided suggestions for clinical applications of rTMS on psychiatric disorders.