RESUMO
ObjectivesTo develop and externally geographically validate a mixed-effects deep learning model to diagnose COVID-19 from computed tomography (CT) imaging following best practice guidelines and assess the strengths and weaknesses of deep learning COVID-19 diagnosis. DesignModel development and external validation with retrospectively collected data from two countries. SettingHospitals in Moscow, Russia, collected between March 1, 2020, and April 25, 2020. The China Consortium of Chest CT Image Investigation (CC-CCII) collected between January 25, 2020, and March 27, 2020. Participants1,110 and 796 patients with either COVID-19 or healthy CT volumes from Moscow, Russia, and China, respectively. Main outcome measuresWe developed a deep learning model with a novel mixed-effects layer to model the relationship between slices in CT imaging. The model was trained on a dataset from hospitals in Moscow, Russia, and externally geographically validated on a dataset from a consortium of Chinese hospitals. Model performance was evaluated in discriminative performance using the area under the receiver operating characteristic (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, calibration performance was assessed using calibration curves, and clinical benefit was assessed using decision curve analysis. Finally, the models decisions were assessed visually using saliency maps. ResultsExternal validation on the large Chinese dataset showed excellent performance with an AUROC of 0.936 (95%CI: 0.910, 0.961). Using a probability threshold of 0.5, the sensitivity, specificity, NPV, and PPV were 0.753 (0.647, 0.840), 0.909 (0.869, 0.940), 0.711 (0.606, 0.802), and 0.925 (0.888, 0.953), respectively. ConclusionsDeep learning can reduce stress on healthcare systems by automatically screening CT imaging for COVID-19. However, deep learning models must be robustly assessed using various performance measures and externally validated in each setting. In addition, best practice guidelines for developing and reporting predictive models are vital for the safe adoption of such models. StatementsThe authors do not own any of the patient data, and ethics approval was not needed. The lead author affirms that this manuscript is an honest, accurate, and transparent account of the study being reported, that no important aspects of the study have been omitted, and that any discrepancies from the study as planned (and, if relevant, registered) have been explained. Patients and the public were not involved in the study. FundingThis study was funded by EPSRC studentship (No. 2110275), EPSRC Impact Acceleration Account (IAA) funding, and Amazon Web Services. SummaryO_ST_ABSWhat is already known on this topicC_ST_ABSO_LIDeep learning can diagnose diseases from imaging data automatically C_LIO_LIMany studies using deep learning are of poor quality and fail to follow current best practice guidelines for the development and reporting of predictive models C_LIO_LICurrent methods do not adequately model the relationship between slices in CT volumetric data C_LI What this study addsO_LIA novel method to analyse volumetric imaging data composed of slices such as CT images using deep learning C_LIO_LIModel developed following current best-practice guidelines for the development and reporting of prediction models C_LI
RESUMO
Objective To observe the clinical effects of modified Shengxian decoction in the treatment of thyroid cancer postoperative hypothyroidism patients.Methods 60 patients of thyroid cancer postoperative hypothyroidism due to deficiency of spleen and kidney were randomly divided into a control group and a treatment group.The control group (28 cases) was by levothyroxine sodium tablets conventional treatment,while the treatment group (32 cases) was treated with Shengxian decoction based on thecontrol group.The changes of the symptom integral and HAMD-17 were observed between two groups before and after treatment.Results After treatment,the total effective rate was 87.5％ in the treatment group and 64.3％ in the control group,the clinical effect of treatment group was significantly better than the control group (x2=4.499,P＜ 0.05).After treatment,the total score of HAMD-17 was 6.8±2.3 in the treatment group and 15.8±2.1 in the control group,both significantly improved than that before the treatment (which were 19.4±1.45 and 18.9± 1.32 respectively).Compared with the control group,the treatment group improved significantly (P＜ 0.01).Conclusion Shengxian decoction plus western medicine has remarkable curative effect in the treatment of thyroid cancer postoperative hypothyroidism,it can improve the depressive state of patients and improve the quality of life.
RESUMO
A Basketball sport is characterized by high exercise intensity, intense antagonism, many physical contacts, and agility. A series of injuries occurs in basketball sports. Tendon adhesion following basketball sports injury is a big problem puzzling athletes for a long time, which affect training and sport technique. Many scholars has been engaged in studying the methods prevent tendon adhesion following basketball sports injury. The article reviews the preventive effects of several biomaterials, such as chitosan, absorbable anti-adhesive film, sodium hyaluronate, polylactic acid, on tendon adhesion following basketball sports injury.
RESUMO
Joint ligament injury often occurs in basketball sports,therefore,research on characteristics of joint cruciate ligament injury is helpful for the prevention and therapy for joint ligament injury.The manuscript introduces the biomechanical characteristics of knee joint cruciate ligament in the moving state,biological problems involved in repair,as well as the application of artificial ligament in knee joint crucriate ligament injury and its advantages and disadvantages.Various kinds of artificial ligament can be used for the repair of ligament injury,such as polyhexene,poly(ethylene terephthalate),carbon fibers,polyester,polydioxnon,polylactic acid.If we can perfect the artificial ligament,it will be more beneficial to its application in repair of ligament injury.
RESUMO
Sports biomechanics, as a branch of biomechanics, studies mechanics characteristics and mechanics relationship of human internal locomotor system and human external bodily movement to fundamentally understand the rule of biomechanics characteristics under the sports condition. Muscular function and mechanics characteristics are a basis of human motion, and muscle mechanics is a basis of sports biomechanics research and sports training.
RESUMO
Sports biomechanics is a strong experimental frontier branches of science and aims to study human body motion,to explore human motion rule by human anatomy,human physiology,mechanics theories and methods. Studies on muscle mechanics are basis of studying sports biomechanics and movement training. Muscular mechanical property is very complex,and related to composition of muscle. Under different sports conditions,biomechanics characteristics of skeletal muscle are different,so the sports injuries are varied.
