Objective To retrospectively analyse pathogenic bacteria isolated from inpatients with lupus erythematosus (SLE) and lupus nephritis (SLE‐LN ) ,and provide references for diagnosis and treatment for these patients with infection . Methods A total of 380 inpatients diagnosed with SLE/SLE‐LN in our hospital from 2010 to 2014 were enrolled in this study ,in‐cluding 96 cases of patients with SLE‐LN .Bacterial inoculation ,culture ,isolation ,identification and drug sensitivity test were carried out .Statistical analysis and susceptibility analysis was performed by using the SPSS 19 .0 and WHONET5 .6 software .Results For patients with SLE and SLE‐LN ,urinary tract infection accounted for 25 .0% and 27 .1% ,hematogenous infection accounted for 8 .1% and 10 .4% ,skin tissue infection accounted for 12 .0% and 8 .3% ,respectively .The most common gram negative bacteria was Escherichia coli ,which accounted for 25 .53% and 30 .21% in patients with SLE and patients with SLE‐LN ,respectively .Followed by Bauman Acinetobacter ,which accounted for 13 .42% and 14 .54% in patients with SLE and patients with SLE‐LN ,respectively . The most common gram positive bacteria was Staphylococcus aureus ,which accounted for 11 .58% and 11 .46% in patients with SLE and patients with SLE‐LN ,respectively .Strains of Escherichia coli were isolated from urine specimens of 69 .79% of patients with SLE and 66 .67% patients with SLE‐LN ,the percentages were significantly higher than that of the conventional urine culture (45% ,P< 0 .01) .The resistance rate of Escherichia coli strains isolated from patients with SLE to quinolones was higher than 66 .00% ,the resistance rate to ampicillin was 89 .69% ,and the resistance rate to piperacillin/tazobactam was low (3 .09% ) .The iso‐lation rates of ESBLs‐producing Escherichia coli strains and ESBLs‐producing Klebsiella pneumoniae strains in patients with SLE‐LN were higher than those in patients with SLE .Conclusion The patients with SLE have a higher risk for infection .The beta‐lac‐tams could be used for the treatment of Escherichia coli urinary tract infection in patients with SLE .

Objective Using healthy female reproductive-age rhesus macaques as the research subjects,we explored the correlation between menstrual cycle abnormalities and gut microbiota composition by using 16S rRNA metagenomic sequencing.Methods Twenty-seven healthy female rhesus macaques were divided into regular menstrual and irregular menstrual groups.Fecal samples were collected at follicular phase(FP),ovulation phase(OP)and luteal phase(LP)of the two groups.The structure and diversity of bacterial flora in different physiological periods were analyzed and compared between the two groups.Results At the phylum level,Firmicutes,Bacteroidetes,and Proteobacteria dominated the sample flora in the follicular,luteal,and ovulatory phases of the rhesus macaques in both the regular and irregular groups,with a combined percentage of more than 98% .At the genus level,the genus Prevotella_9,Ruminococcaceae_UCG-002,Lactobacillus,Prevotella_2,Phascolarctobacterium,Ruminococcaceae_UCG-005,Streptococcus,Blautia,Prevotellaceae_NK3B31_group,Rikenellaceae_RC9_gut_group were dominant.In the luteal phase the percentage of Firmicutes was higher in the regular group than in the irregular group,while the opposite was true for Bacteroidetes.Spirochaetes were higher in the regular group than in the irregular group at all 3 stages(P＜0.05).Conclusion There were some differences in intestinal microbial composition between the two groups of macaques with regular and irregular menstrual cycles,which provided some reference for the study of intestinal bacteria and ovulation disorders.

To construct an intelligent assistant diagnosis model based on the clinical images of basal cell carcinoma (BCC) and pigmented nevi in Chinese by using the advanced convolutional neural network (CNN).
 Methods: Based on the Xiangya Medical Big Data Platform, we constructed a large-scale clinical image dataset of skin diseases according to Chinese ethnicity and the Xiangya Skin Disease Dataset. We evaluated the performance of 5 mainstream CNN models (ResNet50, InceptionV3, InceptionResNetV2, DenseNet121, and Xception) on a subset of BCC and pigmented nevi of this dataset. We also analyzed the basis of the diagnosis results in the form of heatmaps. We compared the optimal CNN classification model with 30 professional dermatologists.
 Results: The Xiangya Skin Disease Dataset contains 150 223 clinical images with lesion annotations, covering 543 skin diseases, and each image in the dataset contains support for pathological gold standards and the patient's overall medical history. On the test set of 349 BCC and 497 pigmented nevi, the optimal CNN model was Xception, and its classification accuracy can reach 93.5%, of which the area under curve (AUC) values were 0.974 and 0.969, respectively. The results of the heatmap showed that the CNN model can indeed learn the characteristics associated with disease identification. The ability of the Xception model to identify clinical images of BCC and Nevi was basically comparable to that of professional dermatologists.
 Conclusion: This study is the first assistant diagnosis study for skin tumor based on Chinese ethnic clinical dataset. It proves that CNN model has the ability to distinguish between Chinese ethnicity's BCC and Nevi, and lays a solid foundation for the following application of artificial intelligence in the diagnosis and treatment for skin tumors.
Area Under Curve ; Carcinoma, Basal Cell ; diagnostic imaging ; Humans ; Neural Networks, Computer ; Nevus, Pigmented ; diagnostic imaging ; Skin Neoplasms ; diagnostic imaging