Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Body weight abnormalities, including overweight, obesity, and underweight, have become a dual public health challenge in Chinese adults: overweight and obesity lead to a variety of chronic complications, while underweight increases the risks of malnutrition, sarcopenia, and organ dysfunction. To systematically address these issues, multidisciplinary experts in endocrinology, sports science, nutrition, and psychiatry from various regions have held multiple weight management seminars. Based on the latest epidemiological data and clinical evidence, they expanded the guideline to include assessment and intervention strategies for underweight, in addition to the core content of obesity management. This guideline outlines the etiological mechanisms, evaluation methods, and multidimensional management strategies for overweight and obesity, covering key areas such as diagnosis and assessment, medical nutrition therapy, exercise prescription, pharmacological intervention, and psychological support. It is intended to provide a scientific and standardized approach to weight management across the adult population, aiming to curb the rising prevalence of obesity, mitigate complications associated with abnormal body weight, and improve nutritional status and overall quality of life.

Objective:To explore the correlation between renal function and abdominal aortic hemodynamic parameters based on four-dimensional flow(4D Flow) MRI in patients with chronic kidney disease (CKD).Methods:A cross-section prospective study was conducted on 73 patients diagnosed with CKD at First People′s Hospital of Changzhou between March 2021 and May 2023, as well as 13 volunteers without kidney injury. According to the estimated glomerular filtration rate (eGFR), the subjects were divided into CKD 1-3 stage group ( n=34), CKD 4-5 stage group ( n=39), and control group ( n=13). All subjects underwent 4D Flow MRI examination of the abdominal aorta, measuring pulse wave velocity (PWV), peak velocity, and maximum wall shear stress (WSS) at the proximal plane (Plane_1) and the higher renal artery opening plane (Plane_2) of the abdominal aorta. The differences in 4D Flow MRI hemodynamic parameters among the three groups were compared using a one-way analysis of variance or the Kruskal-Wallis test. The correlation between 4D Flow MRI hemodynamic parameters and eGFR was analyzed by using the Spearman correlation coefficient. The independent influencing factors that affect eGFR were analyzed by using multivariate linear regression analysis. Results:There were significant differences in abdominal aortic PWV and maximal WSS of Plane_1 and Plane_2 among the three groups ( H=10.38, P=0.006; F=11.16, P<0.001; F=4.75, P=0.011). There were no significant differences in the peak velocity of Plane_1 and Plane_2 among the three groups (both P>0.05). Abdominal aortic PWV was negatively correlated with eGFR ( r s=-0.30, P=0.005). There was a positive correlation between the maximal WSS of Plane_1 and Plane_2 with eGFR ( r s=0.39, P<0.001; r s=0.29, P=0.006). Abdominal aortic PWV and maximal WSS of Plane_1 were independent influencing factors of eGFR (b=-4.32, P=0.018; b=132.23, P=0.004). Conclusions:There is an independent correlation between renal function and abdominal aortic hemodynamic parameters based on 4D Flow MRI in patients with CKD, and abdominal aortic PWV and maximal WSS of Plane_1 were independent influencing factors of eGFR.

AIM To study the chemical constituents from dichloromethane fraction of Dalbergia odorifera T.Chen heartwood.METHODS Separation and purification were performed using silica gel,Sephadex LH-20,thin-layer chromatography,and semi-preparative HPLC,then the structures of obtained compounds were identified by physicochemical properties and spectral data.RESULTS Twenty-four compounds were isolated and identified as 7,2′-dihydroxy-4′-methoxy-isoflavanol(1),vanillin(2),2,2′-oxybis-(1,4-di-tert-butylbenzene)(3),7-hydroxy-6-methoxyflavone(4),sativan(5),5-hydroxy-4′,7-dimethoxyisoflavone(6),2-hydroxy-4,4′-dimethoxychalcone(7),7,2′,3′,4′-tetramethoxydihydroisoflavone(8),2,4,2′-trihydroxy-4′-methoxybenzil(9),ethyl-3-hydroxy-3-phenyl-2-propenoate(10),6,7-dimethoxy-2,3-dihydr-ochromen-4-one(11),sophorophenolone(12),apocynin(13),ethyl-2,4-dihydroxybenzoate(14),ethylparaben(15),methyl-2,4-dihydroxybenzoate(16),5,7-dihydroxy-6-methoxyflavanone(17),7-hydroxyflavanone(18),mimosifoliol(19),7-hydroxy-4′-methoxyisoflavane(20),virolane(21),5-hydroxy-7-methoxychromone(22),3-hydroxyl-5-methoxy-stilbene(23),2′,4′-dihydroxydihydrochalcone(24).CONCLUSION Compound 8 is new natural product,2-6,15,17-18 are isolated from this plant for the first time,7,9-14,16,20-24 are first isolated from genus Dalbergia.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective:To investigate the effects of curcumin,berberine,and puerarin combination therapy on lipid levels in hyperlipidemic mice.Methods:A total of 40 male C57BL/6J mice were randomly divided into eight groups:normal control group(A),high-fat control group(B),curcumin group(C),berberine group(D),puerarin group(E),low-dose combination group of curcumin,berberine,and puerarin(F),high-dose combination group of curcumin,berberine,and puerarin(G),and positive control group(H),with 5 mice in each group.The normal control group was fed a standard diet,while the other groups were given a high-fat diet.After establishing the hyperlipidemic model,the mice were administered with physiological saline,curcumin(200 mg/kg),berberine(200 mg/kg),puerarin(300 mg/kg),low-dose combination of curcumin(50 mg/kg),berberine(50 mg/kg),and puerarin(100 mg/kg),high-dose combination of curcumin(200 mg/kg),berberine(200 mg/kg),and puerarin(300 mg/kg),or simvastatin(6 mg/kg)via gavage for three weeks.After treatment,serum was collected from the mice for biochemical analysis of lipid levels and liver function.Liver tissues were subjected to HE staining,Western blot analysis and real-time quantitative PCR.Results:Curcumin,berberine,and puerarin,whether administered individually or in combination,can reduce the body weight of hyperlipidemic mice(P＜0.01).Treatment with curcumin,berberine,and puerarin individually significantly reduced lipid levels in hyperlipidemic mice(P＜0.05)and alleviated liver damage caused by hyperlipidemia(P＜0.05).Furthermore,the high-dose combination of curcumin,berberine,and puerarin exhibited a more pronounced effect on improving lipid levels(P＜0.01)and provided greater protective effects on the liver compared to the positive control group(P＜0.05).Additionally,curcumin,berberine,and puerarin administered individually can each promote the expression of the LDLR gene in high-fat diet mice(increased by 90％,85％,and 98％,respectively)and reduce the expression of the ACC gene(decreased by 42％,45％,and 43％,respectively).The combination of all three compounds enhances the expression of the LDLR gene in high-fat diet mice(increased by 90％with low-dose combination and 169％with high-dose combination)and reduces the expression of the ACC gene(decreased by 38％with low-dose combination and 42％with high-dose combination).Conclusion:The combination of curcumin,berberine,and puerarin significantly improves lipid levels in hyperlipidemic mice and mitigates liver damage associated with hyperlipidemia.

Objective To design a combat rescue specialized physical training simulator to solve the problems of the existing combat rescue physical traing in multifunctionality and simulation vividness.Methods The simulator was divided into three types for stretcher handling,land combat rescue and marine rescue based on the application scenerio and functional positioning,and into three grades of basic level,intensive level and ultra intensive level based on the loaded mass and additional weight object.The main components of the simulator included a manikin,a bionic joint and addtional weight objects.The manikin was made up of outer skin,inner liner and skeleton;the bionic joint was made of stainless steel with surface electrophoresis treatment,and was composed of high-strength medal bearing shafts with multiple disc springs and damping mechanisms;the additional weight objects involued in high-intensity cast iron or lead blocks,which were pre-embedded,mounted or srtapped into the simulator.The simulator was verified with body shape and mass detection,drop test,waterproof test and drag test.Results It's proved the simulator gained advantages in vividness for body shape and mass,bionic joint structure and adaptability to training environments and could be used for graded physical training in typical combat rescue scenerios.Conclusion The simulator developed solves the problems of the combat rescue specialized physical training equipment,and facilitates the enhancement of physical training of combat rescue personnel.[Chinese Medical Equipment Journal,2025,46(1):33-37]

Objective:To investigate exercise fear condition and its influencing factors in patients with coronary heart dis-ease(CHD)involving in phase Ⅱ cardiac rehabilitation after percutaneous coronary intervention(PCI).Methods:Conven-ience sampling was performed among cardiac rehabilitation patients from a Shanxi grade-A tertiary hospital between Janu-ary 2023 and June 2023.General data questionnaire,Tampa Scale for Kinesiophobia-Short Version for Heart patients(TSK-SV H),the Multidimensional Scale of Perceived Social Support(MSPSS)and the Post Percutaneous Coronary In-tervention Health Literacy Scale(PPCIHLS)were used for assessment.Pearson and Spearman rank correlation analyses were applied to investigate the relationships between social support factors and health literacy factors with patients'fear of exercise;multivariate linear regression models and quantile regression models were used to analyze the influencing factors of fear of exercise.Results:Among the 118 patients,average TSK-SV H score was(33.78±3.79)points;10.2％patients showed significant fear.The correlation analysis showed that PPCIHLS score was negatively correlated with TSK-SV H score(r=-0.423,P＜0.001).Results from multivariate regression analysis indicated that health literacy,cardiac func-tion class and drinking status affected the average score of exercise fear(P＜0.05 all).The quantile regression model pro-vided additional insights,showing that the impact of factors such as living situation,drinking status,cardiac function class and health literacy on exercise fear varied across different quantiles.Notably,cardiac function class had a consistently posi-tive effect on TSK-SV H score at various quantiles.Conclusion:Improving health literacy and tailored rehabilitation plans are vital to reduce exercise fear and improve cardiac rehabilitation effect.