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.

On May 27,2021,the U.S.Food and Drug Administration(FDA)officially approved Lantheus'PYLARIFY?(Piflufolastat F 18,18 F-labeled imaging agent),which can be used for positron emission computed tomography(PET)of prostate-specific membrane antigen(PSMA)-positive lesions in prostate cancer patients to accurately identify prostate cancer with suspected metastasis or recurrence.Piflufolastat F 18 is approved by FDA for two indications.The first is the initial staging for suspected metastatic lesions in men with newly diagnosed prostate cancer.The second is restaging,with the goal of identifying lesions in the setting of biochem ical recurrence.

Objective To investigate the relationship between perioperative nutritional risk and venous thromboembolism(VTE)in patients with hip fracture.Methods A total of 379 patients with unilateral hip fracture due to fall or sprain who underwent elective surgery were selected and divided into the non-VTE group(246 cases)and the VTE group(133 cases)according to whether or not VTE occurred during perioperative period.Basic information,surgical and anesthesia records,nutritional risk related indicators,inflammatory indicators and outcome indicators of patients were collected.Multiple Logistic regression was used to analyze the independent influencing factors of perioperative VTE.Receiver operating characteristics(ROC)curves were used to assess the ability to discriminate independent factors,and DeLong test was used to compare area under the curve(AUC).Results Compared with the non-VTE group,the proportion of patients in the VTE group was older,complicated with hypertension,the time to visit hospital more than 2 days,received(hollow/intramedullary nail)internal fixation,perioperative blood transfusion,ASA gradeⅢtoⅣ,and higher nutritional risk screening Table(NRS)-2002 scores on admission and higher postoperative neutrophil/lymphocyte ratio(NLR).Nutritional prognosis index(PNI),hemoglobin(Hb)and prealbumin(PA)at admission and after operation were lower in the VTE group than those in the non-VTE group(P＜0.01).Multivariate Logistic regression analysis showed that PNI was decreased,NRS-2002 scores and PA were increased,and the time of visit hospital was>2 days after internal fixation.American College of Anesthesiologists(ASA)gradesⅢ-Ⅳwere independent risk factors for perioperative VTE of hip fracture(P＜0.05).ROC curve analysis showed that the AUC(95%CI)of NRS-2002 at admission was 0.739(0.692-0.783),and that of PNI at admission was 0.720(0.672-0.765),both of which were better than other influencing factors(P＜0.01).Conclusion NRS-2002 and PNI are good predictors of perioperative VTE in patients with hip fracture.

ObjectiveExisting artificial vision devices can be divided into two types: implanted devices and extracorporeal devices, both of which have some disadvantages. The former requires surgical implantation, which may lead to irreversible trauma, while the latter has some defects such as relatively simple instructions, limited application scenarios and relying too much on the judgment of artificial intelligence (AI) to provide enough security. Here we propose a system that has voice interaction and can convert surrounding environment information into tactile commands on head and neck. Compared with existing extracorporeal devices, our device can provide a larger capacity of information and has advantages such as lower cost, lower risk, suitable for a variety of life and work scenarios. MethodsWith the latest remote wireless communication and chip technologies, microelectronic devices, cameras and sensors worn by the user, as well as the huge database and computing power in the cloud, the backend staff can get a full insight into the scenario, environmental parameters and status of the user remotely (for example, across the city) in real time. In the meanwhile, by comparing the cloud database and in-memory database and with the help of AI-assisted recognition and manual analysis, they can quickly develop the most reasonable action plan and send instructions to the user. In addition, the backend staff can provide humanistic care and emotional sustenance through voice dialogs. ResultsThis study originally proposes the concept of “remote virtual companion” and demonstrates the related hardware and software as well as test results. The system can not only achieve basic guide functions, for example, helping a person with visual impairment to shop in supermarkets, find seats at cafes, walk on the streets, construct complex puzzles, and play cards, but also can meet the demand for fast-paced daily tasks such as cycling. ConclusionExperimental results show that this “remote virtual companion” is applicable for various scenarios and demands. It can help blind people with their travels, shopping and entertainment, or accompany the elderlies with their trips, wilderness explorations, and travels.

Plant natural products have a wide range of pharmacological properties, not only can they be used as plant dietary supplements to meet the nutritional needs of the human body in the accelerated pace of life, but also occupy an important position in the research and development of therapeutic drugs for the treatment of tumors, inflammation and other diseases, and have been widely accepted by the public due to their good safety. However, despite the above advantages of plant natural products, limiting factors such as low solubility, poor stability, lack of targeting, high toxicity and side effects, and unacceptable odor have greatly impeded their conversion to clinical applications. Therefore, the development of new avenues for the application of new natural products has become an urgent problem to be solved at present. In recent years, with the continuous development of research, various strategies have been developed to improve the bioavailability of natural products. Among them, nanocarrier delivery system is one of the most attractive strategies at present. In past studies, a large number of nanomaterials (organic, inorganic, etc.) have been developed to encapsulate plant-derived natural products for their efficient delivery to specific organs and cells. Up to now, nanotechnology has not only been limited to pharmaceutical applications, but is also competing in the fields of nanofood processing technology and nanoemulsions. Among the various nanocarriers, liposomes are the largest nanocarriers with the largest market share at present. Liposomes are bilayer nanovesicles synthesized from amphiphilic substances, which have advantages such as high drug loading capacity and stability. Attractively, the flexible surface of liposomes can be modified with various functional elements. Functionalized modification of liposomes with different functional elements such as antibodies, nucleic acids, peptides, and stimuli-responsive moieties can bring out the excellent drug delivery function of liposomes to a greater extent. For example, the modification of functional elements with targeting function such as nucleic acids and antibodies on the surface of liposomes can deliver natural products to the target location and improve the bioavailability of drugs; the modification of stimulus-responsive groups such as photosensitizers, magnetic nanoparticles, pH-responsive groups, and temperature sensitizers on the surface of liposomes can achieve controlled release of drugs, localized targeting, and synergistic thermotherapy. In addition to the above properties, by using functionalized liposomes to encapsulate natural products with irritating properties can also effectively mask the irritating properties of natural products, improve public acceptance, and increase the possibility of application of irritating natural products. There are various strategies for modifying liposomes with functional elements, and the properties of functionalized liposomes constructed by different construction strategies differ. The commonly used construction strategies for functionalized liposomes include covalent modification and non-covalent modification. These two types of construction strategies have their own advantages and disadvantages. Covalent modification has better stability than non-covalent modification, but its operation is cumbersome. With the above background, this review focuses on the three typical problems faced by plant natural products at present, and summarizes the specific applications of functionalized liposomes in them. In addition, this paper summarizes the construction strategies for building different types of functionalized liposomes. Finally, this paper will also review the opportunities and challenges faced by functionalized liposomes to enter clinical therapy, and explore the opportunities to overcome these problems, with a view to better realizing the precise control of plant nanomedicines, and providing ideas and inspirations for researchers in related fields as well as relevant industrial staff.

G protein-coupled receptor (GPR) 40, as one of GPRs family, plays a potential role in regulating glucose and lipid metabolism. To study the effect of GPR40 novel agonist SZZ15-11 on hyperglycemia and hyperlipidemia and its potential mechanism, spontaneous type 2 diabetic KKA^y mice, human hepatocellular carcinoma HepG2 cells and murine mature adipocyte 3T3-L1 cells were used. KKA^y mice were divided into four groups, vehicle group, TAK group, SZZ (50 mg·kg^-1) group and SZZ (100 mg·kg^-1) group, with oral gavage of 0.5% sodium carboxymethylcellulose (CMC), 50 mg·kg^-1 TAK875, 50 and 100 mg·kg^-1 SZZ15-11 respectively for 45 days. Fasting blood glucose, blood triglyceride (TG) and total cholesterol (TC), non-fasting blood glucose were tested. Oral glucose tolerance test and insulin tolerance test were executed. Blood insulin and glucagon were measured via enzyme-linked immunosorbent assay (ELISA). After mice′s execution, liver tissue was harvested to test TG and TC content. Then pathological morphology of liver was observed through hematoxylin-eosin (HE) staining, and the lipid metabolism relative signal pathway was analyzed by Western blot and RT-PCR. The experiments were approved by the Institutional Animal Care and Use Committee of the Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College. At the same time, Akt phosphorylation level in HepG2 cells and adiponectin in 3T3-L1 cells treated with TNFα were measured with Western blot. The results show that SZZ15-11 not only decreased blood glucose and lipid, improved insulin sensitivity, but also increased fasting blood glucagon and promoted insulin secretion after glucose loading in KKA^y mice. Additionally, SZZ15-11 alleviated hepatic steatosis and liver dysfunction in KKA^y mice. In liver tissue, SZZ15-11 increased AMPKα phosphorylation level and cholesterol metabolism relative gene Abcg8 transcription. In HepG2 cells, SZZ15-11 increased Akt phosphorylation level. In adipocyte 3T3-L1, SZZ15-11 recovered the decreased adiponectin expression by TNFα. This study proved that GPR40 agonist SZZ15-11 could be a candidate compound for regulating glucolipid metabolic disorder.