ABSTRACT
The onset of rare cardiovascular diseases is early and the mortality is high. The patients of the disease face a long time of hardship in diagnosis and a low treatment rate. As a result, it is urgent to improve the diagnosis and treatment level of rare diseases and to accelerate the selection and R&D of drugs of rare cardiovascular diseases. In recent years, with the rapid development of new technology and basic research, the diagnosis and treatment of rare cardiovascular diseases have made breakthroughs. The article summarizes the research progress in diagnosis and treatment of rare cardiovascular diseases and looks into the future of the research.
ABSTRACT
Objective:To explore the clinical value of peripheral blood lymphocyte subsets in the differential diagnosis of BK virus nephropathy (BKVN) in renal transplantation recipients.Methods:From 2014 to 2018, a total of 172 renal transplant recipients were recruited. Their peripheral blood lymphocyte subsets were detected. According to the pathological puncture results of transplanted kidney, they were divided into acute rejection group (AR, n=68), BKVN group ( n=73) and stable graft function group (STA, n=31). The proportion and absolute number of peripheral blood lymphocyte subsets in each group were measured by flow cytometry and the proportion and absolute count of peripheral blood lymphocyte subsets in each group compared. Results:The proportion and absolute number of CD19 + B cells were markedly lower in BKVN group than those in AR group ( P=0.005, 0.003; 8.5% vs 13.2%, 0.094×10 9/L vs 0.202×10 9/L) and STA group ( P=0.005, 0.003; 8.5% vs 14.8%, 0.094×10 9/L vs 0.198×10 9/L); the proportion of CD3 + CD8 + T cells was significantly higher in BKVN group than that in AR group ( P=0.013; 36.9% vs 31.2%). In addition, no obvious difference existed in the proportion and absolute number of lymphocytes, CD3 + T, CD3 + CD4 + T and CD16 + CD56 + natural killer (NK) among three groups ( P>0.05). No obvious difference existed in the proportion of CD3 + CD4 + / CD3 + CD8 + T cells among three groups ( P>0.05). Conclusions:No difference exists in T cell-related lymphocyte subsets between BKVN and acute rejection recipients. However, the number and proportion of CD19 + B cells decrease markedly in BKVN.
ABSTRACT
Objective To develop and validate a model based on deep learning for automatic diagnosis of early gastric cancer ( EGC) to improve detection and diagnosis of EGC. Methods A total of 5159 images ( including 1000 images of EGC and 4159 images of other benign lesions or normal patients) obtained from May 2014 to December 2016 were collected from endoscopic database in changhai Hospital. Then 4449 images were selected randomly for a deep convolutional neural network ( CNN ) training, of which 768 were diagnosed as EGC and 3681 diagnosed as other benign lesions or normal. The remaining 710 images were used to test the model by comparing with diagnostic results of four endoscopists. Results The deep learning model showed accuracy of 89. 4％ ( 635/710 ) , sensitivity of 88. 8％ ( 206/232 ) and specificity of 89. 7％ ( 429/478) for EGC. The mean time required for diagnosis was 0. 30 ± 0. 02 s. The performance of the model was superior to that of four endoscopists. Conclusion The model based on deep learning has high accuracy,sensitivity and specificity for detecting EGC,which could assist endoscopists in real-time diagnosis.