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.

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.

Thrombus is a major factor leading to cardiovascular diseases such as myocardial infarction and stroke. Although fibrinolytic anti-thrombotic drugs have been widely used in clinical practice, they are still limited by narrow therapeutic windows, short half-lives, susceptibility to inactivation, and abnormal bleeding caused by non-targeting. Therefore, it is crucial to effectively deliver thrombolytic agents to the site of thrombus with minimal adverse effects. Based on the long blood circulation and excellent drug-loading properties of human serum albumin (HSA), we employed genetic engineering techniques to insert a functional peptide (P-selectin binding peptide, PBP) which can target the thrombus site to the N-terminus of HSA. The fusion protein was expressed using Pichia pastoris and purified by Ni-chelating affinity chromatography. After being loaded with gold nanoparticles (Au NPs), the fusion protein formed homogeneous and stable nanoparticles (named as PBP-HSA@Au) with a diameter of 17.7 ± 1.0 nm and a zeta potential of -11.3 ± 0.2 mV. Cytotoxicity and hemolysis tests demonstrated the superb biocompatibility of PBP-HSA@Au. Platelet-targeting experiments confirmed the thrombus-targeting ability conferred by the introduction of PBP into PBP-HSA@Au. Upon near-infrared ray (NIR) irradiation, PBP-HSA@Au rapidly converted light energy into heat, thereby disrupting fibrinogen and exhibiting outstanding thrombolytic efficacy. The designed HSA fusion protein delivery system provides a precise, rapid, and drug-free treatment strategy for thrombus therapy. This system is characterized by its simple design, high biocompatibility, and strong clinical applicability. All animal experiments involved in this study were carried out under the protocols approved by the Animal Experiment Ethics Committee of Jiangnan University [JN. No20230915S0301015(423)].

From the perspective of the physiological basis of liver and kidney sharing the common source in traditional Chinese medicine(TCM),and by integrating the theory of kidney dominating bone,liver dominating tendon,and meridian sinew of TCM as well as the bone resorption and collapse theory,and non-uniform settlement theory and lower-limb musculoskeletal bowstring structure theory of modern orthopedics,the pathogenesis of osteonecrosis of the femoral head(ONFH)under the system of non-uniform settlement during bone resorption and multidimensional composite bowstring working in coordination with the theory of liver-kidney and muscle-bone was explored.The key to the TCM pathogenesis of ONFH lies in the deficiency of the liver and kidney,and then the imbalance of kidney yin-yang leads to the disruption of the dynamic balance of bone formation and bone resorption mediated by osteoblasts-osteoclasts,which manifests as the elevated level of bone metabolism and the enhancement of focal bone resorption in the femoral head,and then leads to the necrosis and collapse of the femoral head.It is considered that the kidney dominates bone,liver dominates tendon,and the tendon and bone together constitute the muscle-bone-joint dynamic and static system of the hip joint.The appearance of collapse destroys the originally balanced muscle-bone-joint system.Moreover,the failure of liver blood in the nourishment of muscles and tendons further exacerbates the imbalance of the soft tissues around the hip joint,accelerates the collapse of the muscle-bone-joint dynamic and static system,speeds up the process of femoral head collapse,and ultimately results in irreversible outcomes.Based on the above pathogenesis,the systematic integrative treatment of ONFH should be based on the TCM holistic concept,focuses on the focal improvement of internal and external blood circulation of the femoral head by various approaches,so as to rebuild the coordination of joint function.Moreover,attention should be paid to the physical constitution of the patients,and therapy of tonifying the kidney and regulating the liver can be used to restore the balance between osteogenesis and osteoblastogenesis,and to reconstruct the muscle-bone-joint system,so as to effectively delay or even prevent the occurrence of ONFH.

This article discussed the evolution of the traditional preparation process of Pinelliae Rhizoma Fermentata.The production methods for Pinelliae Rhizoma Fermentata in Song Dynasty include cake-making of Pinelliae Rhizoma together with ginger juice and fermentation after cake-making,and the former method of cake-making was the mainstream.The process technology in Jin and Yuan Dynasties inherited from that in Song Dynasty,and the application of Pinelliae Rhizoma Fermentata had certain limitations.The medical practitioners of Ming Dynasty elucidated the mechanism of processing of Pinelliae Rhizoma Fermentata,and proposed the view of"sliced Pinelliae Rhizoma being potent while fermented Pinelliae Rhizoma being mild".In the Ming Dynasty,LI Shi-Zhen defined the cake-making process and fermentation process for Pinelliae Rhizoma,and HAN Mao's Han Shi Yi Tong(Han's Clear View of Medicine)contained five prescriptions for the processing of Pinelliae Rhizoma Fermentata,which had the epoch-making signficance in the expansion of prescriptions for the processing of Pinelliae Rhizoma Fermentata.In the Qing Dynasty,HAN Fei-Xia's ten methods for making Pinelliae Rhizoma Fermentata were summarized on the basis of the methods recorded in Han Shi Yi Tong,and at that time,the processing of Pinelliae Rhizoma Fermentata and the preparation of Massa Medicata Fermentata interacted with each other.After the founding of the People's Republic of China,the local experience in the preparation of Pinelliae Rhizoma Fermentata was deeply influenced by the methods in the Qing Dynasty,and the local preparation technical standards gradually became the same.Moreover,this article also explored the issues of the importance of"Pinelliae Rhizoma"and"ingredients for fermentation",the pre-treatment of Pinelliae Rhizoma,the distinction between cake-making process and fermentation process for Pinelliae Rhizoma,the amount of flour added as well as the timing of adding,the addition of Massa Medicata Fermentata powder,the role of Alum in Pinelliae Rhizoma Fermentata and so on.

Objective: To explore the mechanism by which icariin alleviates viral myocarditis. Methods: CVB3-induced cardiomyocytes were used as an in vitro model of viral myocarditis to assess the effects of icariin treatment on cell viability, inflammation, and apoptosis. Moreover, the effects of icariin on ferroptosis and TLR4 signaling were assessed. After AC16 cells were transfected with TLR4 overexpression plasmids, the role of TLR4 in mediating the regulatory effect of icariin in viral myocarditis was investigated. Results: Icariin significantly elevated cell viability and reduced inflammatory factors TNF-α, IL-1β, IL-6, and IL-18. Flow cytometry revealed that icariin decreased apoptosis rate, and the protein expression of Bax and cleaved caspase 3 and 9 in CVB3-induced cardiomyocytes. Additionally, it suppressed ferroptosis including lipid peroxidation and ferrous ion, as well as the TLR4 signaling. However, TLR4 overexpression abrogated the modulatory effects of icariin. Conclusions: Icariin mitigates CVB3-induced myocardial injury by inhibiting TLR4-mediated ferroptosis. Further animal study is needed to verify its efficacy.

AIM To investigate the effects of astragaloside IV on improving insulin resistance(IR)in obese rat model of polycystic ovary syndrome(PCOS),and to analyze its effect on ovarian MAPK/ERK pathway as well.METHODS The obese PCOS rat models established by feeding of letrozole combined with high-fat and high-sugar diet were randomly divided into the model group,the metformin(135 mg/kg)group and the low-dose and high-dose astragaloside Ⅳ(25,50 mg/kg)groups,with 8 rats in each group in contrast to those of the control group.After 21 days oral administration,the rats had their body weight recorded;their ovarian index calculated;their levels of fasting blood glucose(FBG),serum triglyceride(TG),total cholesterol(TC),follicle-stimulating hormone(FSH),testosterone(T),estradiol(E2),luteinizing hormone(LH)and fasting insulin(FINS)measured;their HOMA-IR and LH/FSH values calculated;their ovarian expressions of MAPK/ERK pathway related proteins detected by Western blot;and their ovarian expression of vascular endothelial growth factor(VEGF)protein detected by immunofluorescence staining.RESULTS Compared with the control group,the model group showed increased polycystic pathological changes,levels of body weight,ovarian index,serum TG,TC,LH,FSH,T,FINS,and FBG,values of LH/FSH and HOMA-IR,and ovarian p-ERK1/2/ERK1/2,p-MEK1/2/MEK1/2,p-Raf/Raf,and VEGF protein expressions(P<0.01);and decreased serum E2 level(P<0.01).Compared with the model group,both astragaloside Ⅳ and metformin groups shared significantly alleviated ovarian polycystic lesions,and decreased body weight,levels of ovarian index,serum TG,TC,LH,FSH,T,FINS,and FBG,values of LH/FSH and HOMA-IR,ovarian p-ERK1/2/ERK1/2,p-MEK1/2/MEK1/2,p-Raf/Raf,and VEGF protein expressions(P<0.05,P<0.01),and increased serum E2 level(P<0.05,P<0.01).CONCLUSION Upon the obese PCOS rat models,astragaloside Ⅳ can antagonize their IR,improve their hormone levels and alleviate their ovarian lesions via inhibiting the activation of MAPK/ERK pathway.