Objective To investigate the clinical characteristics of multisystem impairment of Sj(o)gren's syndrome (SS) to make quick and accurate diagnose and treatment to decrease the rate of misdiagnosis and mistreatment.Methods A case of thrombotic thrombocytopenic purpura with SS was reported and the related literatures were reviewed.The clinical manifestations,laboratory examinations,diagnostic criteria and therapy of thrombotic thrombocytopenic purpura with SS were analyzed.Results Purpura haemorrhagica,hemolytic anemia,central nervous systemic symptoms,kidney impairment and fever were the representative clinical manifestations of thrombotic thrombocytopenic purpura with SS.Plasmapheresis was the most effective therapy with the background treatment with glucocorticosteroid and immunosuppressive agents.Conclusion Thrombotic thrombocytopenic purpura with SS presents a complicated clinical manifestations,so misdiagnosis and mistreatment is very frequent.More attention should be paid to this specific situation because the disease is rare and has high mortality rate.

OBJECTIVE: To propose a coupled convolutional and graph convolutional network (CCGCN) model for diagnosis of Alzheimer's disease (AD) and its prodromal stage. METHODS: The disease-related brain regions generated by group-wise comparison were used as the input. The convolutional neural networks (CNNs) were used to extract disease-related features from different locations on brain magnetic resonance (MR) images. The generated features via the graph convolutional network (GCN) were processed, and graph pooling was performed to analyze the inherent relationship between the brain topology and the diagnosis task adaptively. Through ADNI dataset, we acquired the accuracy, sensitivity and specificity of the diagnosis tasks for AD and its prodromal stages, followed by an ablation study on the model structure. RESULTS: The CCGCN model outperformed the current state-of-the-art methods and showed a classification accuracy of 92.5% for AD with a sensitivity of 88.1% and a specificity of 96.0%. CONCLUSIONS Based on the structural and topological features of the brain MR images, the proposed CCGCN model shows excellent performance in AD diagnosis and is expected to provide important assistance to physicians in disease diagnosis.
Alzheimer Disease ; diagnostic imaging ; Brain ; Humans ; Magnetic Resonance Imaging ; Neural Networks, Computer

In order to evaluate the efficacy and safety of Hexue Mingmu tablets in the treatment of diabetic retinopathy（DR） and retinal vein obstruction（RVO）， and to provide a basis for the clinical treatment of ophthalmic diseases， this paper obtained randomized controlled trials（RCTs） of Hexue Mingmu tablets in the treatment of DR and RVO by searching Chinese and English electronic databases and trial registration platforms（up to September 13， 2022）. The risk of bias in the included studies was assessed using RoB2.0， and Meta-analysis was performed using RevMan5.4. A total of 35 RCTs involving a total sample size of 3 261 patients were included. Meta-analysis results showed that compared with conventional western medical treatment alone， the combination of Hexue Mingmu tablets with conventional western medical treatment improved patients' macular thickness｛mean difference（MD） =-39.83， 95% confidence interval（CI） ［-51.60， -28.06］， P<0.000 01｝， improved corrected visual acuity｛risk ratio（RR）_dichotomous=1.09， 95% CI ［1.00， 1.18］， P=0.04； MD_{continuous variable}=0.15， 95% CI ［0.13， 0.17］， P<0.000 01｝， increased effective rate of fundus symptom improvement（RR=1.26， 95% CI ［1.22， 1.30］， P<0.000 01）， improved hemorheology index｛standard mean difference（SMD）=-1.53， 95% CI ［-2.04， -1.01］， P<0.000 01｝， shortened improvement time of fundus symptoms（MD=-5.53， 95% CI ［-5.96， -5.09］， P<0.000 01）， and there was no significant difference on adverse events between the two groups. The results show that treatment of DR and RVO with Hexue Mingmu tablets may improve the macular thickness and hemorheology index of patients， which can significantly enhance the effect of corrected visual acuity and clinical efficiency， and shorten the time to symptom improvement. However， the original literature is of low quality and the pooled results have some limitations. Subsequent studies should try to use uniform standard assessment criteria and testing methods， focus on the rigor of study design and implementation， and pay attention to the key outcomes of this disease and the clinical safety of medication， so as to provide more reliable evidence to support this kind of clinical problems.