Objectives: Coronavirus disease 2019 (COVID-19) is sweeping the globe and has resulted in infections in millions of people. Patients with COVID-19 face a high fatality risk once symptoms worsen; therefore, early identification of severely ill patients can enable early intervention, prevent disease progression, and help reduce mortality. This study aims to develop an artificial intelligence-assisted tool using computed tomography (CT) imaging to predict disease severity and further estimate the risk of developing severe disease in patients suffering from COVID-19. Materials and Methods: Initial CT images of 408 confirmed COVID-19 patients were retrospectively collected between January 1, 2020 and March 18, 2020 from hospitals in Honghu and Nanchang. The data of 303 patients in the People's Hospital of Honghu were assigned as the training data, and those of 105 patients in The First Affiliated Hospital of Nanchang University were assigned as the test dataset. A deep learning based-model using multiple instance learning and residual convolutional neural network (ResNet34) was developed and validated. The discrimination ability and prediction accuracy of the model were evaluated using the receiver operating characteristic curve and confusion matrix, respectively. Results: The deep learning-based model had an area under the curve (AUC) of 0.987 (95% confidence interval [CI]: 0.968-1.00) and an accuracy of 97.4% in the training set, whereas it had an AUC of 0.892 (0.828-0.955) and an accuracy of 81.9% in the test set. In the subgroup analysis of patients who had non-severe COVID-19 on admission, the

Objective: To observe the significance of subchondral bone microfracture in the human osteoarthritic tibial plateau on cartilage tidemark drift.Methods: Human knee tibial plateau cartilage samples with different OARSI grades were obtained, and the numbers of cartilage tidemarks and microfracture lines were determinedafter safranin O staining and compared among groups. Osteogenesis caused by microfracture in subchondral bone was observed and staged according to biological properties.Immunohistochemistry, western blotting, PCR and laser microdissection were performedto detect the biological properties of osteogenic areas caused by microfractures.The accompanying relationship between the ossification process and new tidemark formation inosteogenic areas caused by microfractures was then evaluated.Results: With the increase in OARSI grade, the numbers of cartilage tidemarks and subchondral bone microfracture lines in human knee tibial plateau cartilage tissue samples showed increasing trends.The subchondral bone microfracture line was observed toextend as far asthe basal area of hyaline cartilage and cause endochondral osteogenesis.The endochondral osteogenesis caused by subchondral microfracture was categorized into chondrocyte,calcareous sedimentary and ossification stages. A new tidemark appeared in the osteogenic region near the hyaline cartilage when the ossification process of the osteogenic region was completed.Conclusions:Endochondral osteogenesis canoccur at the base of hyaline cartilage induced by microfractures in the tibial plateau subchondral bone. A new cartilage tidemark can form on the side of the osteogenic tissue close to hyaline cartilage when the process of osteogenesis is completed.There is a positive correlation between the degree of cartilage tissue degeneration and the number of tidemarks in articular cartilage.