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:This study aims to investigate the predictive performance of serum levels of white blood cell count(WBC),D-dimer(D-D)and N-terminal pro-brain natriuretic peptide(NT-proBNP)for major adverse cardiovascular events(MACE)in elderly patients with acute ST-segment elevation myocardial infarction(ASTE-MI).Methods:A total of 70 elderly patients with ASTEMI treated in Bozhou People's Hospital between April 2020 and May 2023 were prospectively selected as observation group.Incidence of MACE during 1-year follow-up were recorded,another 50 patients with unstable angina pectoris treated in our hospital simultaneously were selected as control group.Serum levels of WBC,D-D and NT-proBNP were compared among above groups.The receiver operating characteristic(ROC)curve was used to evaluate the predictive value of serum WBC,D-D and NT-proBNP for MACE in elderly patients with ASTEMI.A nomogram was established,and calibration curve and deci-sion curve analysis(DCA)were used to evaluate the performance of model.Results:A total of 40 cases(59.70％)experienced MACE during one-year follow-up.Compared to those in control group,patients in observation group had significant higher serum WBC[(11.43±1.98)×109/Lvs.(6.30±1.99)× 109/L],D-D[(0.91±0.20)mg/L vs.(0.47±0.18)mg/L]andNT-proBNP[(192.31±63.19)pg/ml vs.(114.05±22.79)pg/ml](P＜0.001 all).Compared to participants without MACE,those with MACE had significantly higher serum WBC[(13.33±1.90)× 109/L vs.(10.27±0.98)× 109/L],D-D[(1.11±0.25)mg/L vs.(0.87±0.21)mg/L]and NT-proBNP[(238.73±50.22)pg/ml vs.(150.70±39.16)pg/ml](P＜0.001 all).ROC analysis showed that the ar-ea under the curve(AUC)of the combined detection of serum WBC(AUC=0.791,95％CI 0.677～0.879),D-D(AUC=0.767,95％CI 0.650～0.859)and NT-proBNP(AUC=0.733,95％CI 0.614～0.832)was 0.916(95％CI 0.825～0.969),which was significantly higher than those of single detections(Z=2.386,4.953,3.190,P=0.017,0.004,＜0.001).The total score of the nomogram model constructed based on the levels of WBC,D-D and NT-proBNP ranged from 70 to 126 points.The predicted incidence was basically consistent with the actual in-cidence.For the internal verification of the model,the AUC of ROC curve of the training set and the validation set was 0.863 and 0.926 respectively.The DCA curve was located above the critical curve,indicating that the model had a net benefit and good clinical effectiveness.Conclusion:Serum WBC,D-D and NT-proBNP significantly el-evated in elderly patients with ASTEMI.The combined detection of serum WBC,D-D and NT-proBNP levels has good predictive value for MACE in these patients.

Kv1.3,a voltage-gated potassium channel,is highly expressed in T lymphocytes,the nervous system,and vascular smooth muscle cells.It plays a critical role in membrane excitability and electrical signal transduction,serving as an important target for studying T-cell function and providing a promising direction for developing therapeutics against autoimmune and inflammatory diseases.Therefore,the de-velopment of specific inhibitors of Kv1.3 channel has emerged as a novel therapeutic strategy for these disorders.In this study,we isolated and purified a novel Kv1.3-inhibitory peptide toxin,LmKTx13,from the venom of the scorpion Lychas mucronatus using reversed-phase high-performance liquid chroma-tography(RP-HPLC).LmKTx13 consists of 38 amino acid residues,including six cysteines that form three disulfide bonds.Whole-cell patch-clamp recordings revealed that LmKTx13 potently inhibited Kv1.3 with an IC50 of 7.92±3.0 nmol/L.Selectivity analysis showed that 2 μmol/L LmKTx13 also in-hibited Kv1.2 and Kv1.7,but exhibited no significant effects on other potassium channel subtypes or voltage-gated sodium channels.Further investigation into the mechanism demonstrated that LmKTx13 acts as a pore-blocking inhibitor of Kv1.3.By analyzing the effects of LmKTx13 on Kv1.3 channel gating ki-netics and performing sequence alignment of the pore regions of Kv1.3 and Kv1.5,we constructed site-directed mutants and identified the pore region of Kv1.3 as the critical binding site for LmKTx13.Key residues involved in the interaction included T425,G427,and H451.In summary,we discovered a no-vel pore-blocking Kv1.3 inhibitor,LmKTx13,from L.mucronatus venom,which exhibits high affinity and selectivity for Kv1.3.These findings highlight its potential as a potential lead molecule for developing Kv1.3-targeted therapeutics.

Objective To explore the predictive factors of recurrence of chronic suppurative otitis media(CSOM)after otoendoscopic surgery,and construct a risk quantified nomogram model.Methods The clinical data of 485 patients with CSOM who underwent otoendoscopic surgery in our hospital from February 2021 to February 2023 were retrospectively analyzed.The patients were divided into the recurrence group and the non-recurrence group according to the recurrence situation during the follow-up period.The clinical data of patients between the two groups were compared,and the predictive factors of postoperative recurrence were analyzed by Cox regression method.A risk quantified nomogram model was constructed based on these predictive factors.The predictive efficiency of the model was verified by receiver operating characteristic(ROC)curve,and the calibration degree of the model was verified by Hosmer-Lemeshow goodness of fit analysis,and the clinical net benefit of the model was evaluated by decision curve analysis(DCA)method.Results Follow-up ranged from 6 to 39 months,with a median of 21(11,32)months,the postoperative recurrence rate was 14.64%(71/485).Combined with recurrent upper respiratory tract infections(HR=3.019,95%CI:1.609 to 5.664),combined with chronic rhinosinusitis(HR=2.428,95%CI:1.529 to 3.856),combined with adenoid hypertrophy(HR=2.214,95%CI:1.381 to 3.551),middle ear risk index(MERI)score(HR=2.863,95%CI:1.445 to 5.675),the seven-item eustachian tube dysfunction questionnaire(ETDQ-7)score(HR=2.679,95%CI:1.505 to 4.765)and inadequate drainage of the surgical cavity(HR=2.373,95%CI:1.503 to 3.746)were the risk factors for postoperative recurrence(P<0.05).A risk quantified nomogram model of recurrence after otoendoscopic surgery in CSOM patients was constructed based on the predictive factors of Cox regression analysis,among them the risk value ranges of patients who combined with recurrent upper respiratory tract infections,combined with chronic rhinosinusitis,combined with adenoid hypertrophy,MERI score,ETDQ-7 score,and inadequate drainage of the surgical cavity were 0 to 65 points,0 to 56 points,0 to 52 points,0 to 76 points,0 to 64 points,and 0 to 76 points,respectively.The area under the curve of ROC,sensitivity and specificity of the model for predicting postoperative recurrence were 0.928(95%CI:0.875 to 0.948),85.92%and 88.89%,respectively.There was no significant difference between the predicted probability of postoperative recurrence and the actual probability(P>0.05).The threshold probability of postoperative recurrence predicted by the model in the range of 4%to 92%could obtain clinical net benefit.Conclusion The predictive factors of recurrence after otoendoscopic surgery in CSOM patients include combined with recurrent upper respiratory tract infections,combined with chronic rhinosinusitis,combined with adenoid hypertrophy,MERI score,ETDQ-7 score and inadequate drainage of the surgical cavity,the risk quantified nomogram model based on these factors is highly effective in predicting postoperative recurrence.