Qing Lv

BACKGROUND: China has a large population; however, medical resources are unevenly distributed and extremely limited, and more medical services are needed. With the development and ever-increasing popularity of mobile internet communication, China has created a mode of mobile health (mHealth) care to resolve this problem. OBJECTIVE: The aim of this study was (1) to describe the problems associated with China's medical care practice, (2) explore the need for and the feasibility of internet-based medical care in China, and (3) analyze the functionality of and services offered by internet-based health care platforms for the management of chronic diseases. METHODS: Data search was performed by searching national websites, the popular search engine Baidu, the App Store, and websites of internet medical care institutions, using search terms like "mobile health," "Internet health," "mobile medical," "Internet medical," "digital medical," "digital health," and "online doctor." A total of 6 mobile apps and websites with the biggest enrollment targeting doctors and end users with chronic diseases in China were selected. RESULTS: We recognized the limitations of medical and health care providers and unequal distribution of medical resources in China. An mHealth care platform is a novel and efficient way for doctors and patients to follow up and manage chronic diseases. Services offered by these platforms include reservation and payment, medical consultation, medical education assessment, pharmaceutical and medical instruments sales, electronic medical records, and chronic disease management. China's health policies are now strongly promoting the implementation of mHealth solutions, particularly in response to the increasing burden of chronic diseases and aging in the population. CONCLUSIONS: China's internet-based medical and health care mode can benefit the populace by providing people with high-quality medical resources. This can help other countries and regions with high population density and unevenly distributed medical resources manage their health care concerns.

Not only were traditional artificial neural networks and machine learning difficult to meet the processing needs of massive images in feature extraction and model training but also they had low efficiency and low classification accuracy when they were applied to image classification. Therefore, this paper proposed a deep learning model of image classification, which aimed to provide foundation and support for image classification and recognition of large datasets. Firstly, based on the analysis of the basic theory of neural network, this paper expounded the different types of convolution neural network and the basic process of its application in image classification. Secondly, based on the existing convolution neural network model, the noise reduction and parameter adjustment were carried out in the feature extraction process, and an image classification depth learning model was proposed based on the improved convolution neural network structure. Finally, the structure of the deep learning model was optimized to improve the classification efficiency and accuracy of the model. In order to verify the effectiveness of the deep learning model proposed in this paper in image classification, the relationship between the accuracy of several common network models in image classification and the number of iterations was compared through experiments. The results showed that the model proposed in this paper was better than other models in classification accuracy. At the same time, the classification accuracy of the deep learning model before and after optimization was compared and analyzed by using the training set and test set. The results showed that the accuracy of image classification had been greatly improved after the model proposed in this paper had been optimized to a certain extent.

BACKGROUND: Studies into ankylosing spondylitis (AS) and its relationship with immune imbalance are controversial, and the correlation between the efficacy of TNF-α inhibitor and changes in immune imbalance is unclear. METHODS: A total of 40 immune cells were tested with flow cytometry, and the results of 105 healthy control (HC) subjects, 177 active-stage AS patients, and 23 AS cases before and after 12 weeks of TNF-α inhibitor therapy (Anbainuo) were analyzed. RESULTS: Compared with the HC group, the proportion of immune cells, such as naïve and central memory CD4+T cells, in AS increased (P < 0.0001), but effector memory and terminally differentiated CD4+T cells were decreased (P < 0.01 and 0.0001, respectively). Naïve, central memory, and effector memory CD8+T cells were increased (P < 0.0001, 0.001, and 0.01, respectively), but terminally differentiated CD8+T cells were decreased (P < 0.0001). Th1 cells (helper T cells-1), Tfh1 cells (follicular helper T cells-1), Tc1 cells (cytotoxic T cells-1), and Tregs (regulatory T cells) were lower (P < 0.01, 0.05, 0.0001, and 0.001, respectively), but Th17 cells, Tfh17 cells, and Tc cells were higher (P < 0.001, 0.0001, and 0.001, respectively). The proportions of total B cells and class-switched B cells were increased (P < 0.05), but non-switched B cells, plasma cells, memory B cells, and immature Bregs (regulatory B cells) were lower (P < 0.01, 0.0001, 0.0001, and 0.0001, respectively). After Anbainuo therapy, the percentage of naïve CD4+ T cells had decreased (P < 0.05) but Tregs and B10 cells (IL-10-producing regulatory B cells) had increased (P < 0.01 and 0.05, respectively), and the increase in Tregs was positively correlated with the decrease in C-reactive protein (CRP) (r = 0.489, P = 0.018). CONCLUSIONS: We found that active-stage AS patients have an immunity imbalance of frequency involving multiple types of immune cells, including CD4+T cells, CD8+T cells, Th cells, Tfh cells, Tc cells, Tregs, Bregs, and B cells. TNF-α inhibitor Anbainuo can not only help to inhibit disease activity but can also improve the immune imbalance of CD4+ T cells and negative regulatory cells in frequency. But CD8+ T cells have not been rescued.