Gut microbiota develops to an adult-like mode in early life and stays comparatively stable since then. There are 3 stages in early life: delivery, breastfeeding, and post-weaning nutrition period. In our study, we ascertained the forming of adult-like microbiota pattern in early life time by establishing antibiotic-treated mice model and analyzed the residential microorganism of whole gastrointestinal tract using 16S rRNA sequencing. The antibiotic-treated mouse model showed antibiotics could influence gut bacterial development and breastfeeding is the critical period for gastric and ileal microbiota development. In this study, we were the first to investigate the residential bacteria in the whole gastrointestinal tract in early life time. With our approach of exploration of gut microbiota evolution, we hope to provide a better view of how residential microflora develop in early life and influence the future gut microbial system, which help us better understand gut microbiota and related diseases.

Among the extraintestinal ocular manifestations of patients with inflammatory bowel disease (IBD), episcleritis is associated with the inflammatory activity of IBD. The use of artificial intelligence to evaluate scleral images may help establish a non-invasive method for assessing the degree of inflammation. This study aims to provide a new approach for evaluating IBD inflammation by analyzing scleral images. We collected scleral images from patients with IBD across different inflammatory states and from controls. Then, we analyzed the images using the MASK R-CNN and HRNet method to build models for assessing the degree of inflammation. A total of 942 scleral images were collected and divided into 5 groups: the control group, inflammatory Crohn’s disease (ICD) group, CD in remission (RCD) group, inflammatory ulcerative colitis (IUC) group, and UC in remission (RUC) group. In the training set, the accuracy and F1-score for discriminating between IBD and non-IBD controls, inflammatory IBD and IBD in remission, ICD and RCD, IUC and RUC were 99.02

n clinical, if a patient presents with nonmechanical obstructive dysphagia, esophageal chest pain, and gastro esophageal reflux symptoms, the physician will usually assess the esophageal dynamic function. High-resolution manometry (HRM) is a clinically commonly used technique for detection of esophageal dynamic function comprehensively and objectively. However, after the results of HRM are obtained, doctors still need to evaluate by a variety of parameters. This work is burdensome, and the process is complex. We conducted image processing of HRM to predict the esophageal contraction vigor for assisting the evaluation of esophageal dynamic function. Firstly, we used Feature-Extraction and Histogram of Gradients (FE-HOG) to analyses feature of proposal of swallow (PoS) to further extract higher-order features. Then we determine the classification of esophageal contraction vigor normal, weak and failed by using linear-SVM according to these features. Our data set includes 3000 training sets, 500 validation sets and 411 test sets. After verification our accuracy reaches 86.83%, which is higher than other common machine learning methods.

Crohn’s disease (CD) and intestinal tuberculosis (ITB) have many similarities and overlaps in their clinical manifestations and medical imaging features, which makes it difficult to accurately differentiate CD from ITB. Random forests have unique advantages in discovering specific indicators and measuring relevance. By fusing the attributes and the correlation information between the sample and training set, we propose a fusion correlation neural network (FCNN) to diagnose CD and ITB patients. A total of 287 cases with fifty-nine indicators were collected from the Second Xiangya Hospital of Central South University. An FCNN allows one to explain the feature selection and learning classification rules in neural networks. The experiments show that perianal fistulas, skin and mucosal lesions, intestinal perforation, comb sign, and cobblestone appearance tend to be associated with CD; and ascites show a higher association with intestinal tuberculosis. These conclusions are consistent with the experience of clinicians. Finally, the age, disease course, white blood cell, hemoglobin, platelets, C-reactive protein, and T-SPOT of patients were used to train the FCNN. The average accuracy of the FCNN exceeds 91%, showing better performance than existing linear regression standards and other machine learning models.

In countries with a high incidence of tuberculosis, the typical clinical features of Crohn's disease (CD) may be covered up after tuberculosis infection, and the identification of atypical Crohn's disease and intestinal tuberculosis (ITB) is still a dilemma for clinicians. Least absolute shrinkage and selection operator (LASSO) regression has been applied to select variables in disease diagnosis. However, its value in discriminating ITB and atypical Crohn's disease remains unknown. A total of 400 patients were enrolled from January 2014 to January 2019 in second Xiangya hospital Central South University.Among them, 57 indicators including clinical manifestations, laboratory results, endoscopic findings, computed tomography enterography features were collected for further analysis. R software version 3.6.1 (glmnet package) was used to perform the LASSO logistic regression analysis. SPSS 20.0 was used to perform Pearson chi-square test and binary logistic regression analysis. In the variable selection step, LASSO regression and Pearson chi-square test were applied to select the most valuable variables as candidates for further logistic regression analysis. Secondly, variables identified from step 1 were applied to construct binary logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was performed on these models to assess the ability and the optimal cutoff value for diagnosis. The area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy rate, together with their 95% confidence and intervals (CIs) were calculated. MedCalc software (Version 16.8) was applied to analyze the ROC curves of models. 332 patients were eventually enrolled to build a binary logistic regression model to discriminate CD (including comprehensive CD and tuberculosis infected CD) and ITB. However, we did not get a satisfactory diagnostic value via applying the binary logistic regression model of comprehensive CD and ITB to predict tuberculosis infected CD and ITB (accuracy rate:79.2%VS 65.1%). Therefore, we further established a binary logistic regression model to discriminate atypical CD from ITB, based on Pearsonchi-square test (model1) and LASSO regression (model 2). Model 1 showed 89.9% specificity, 65.9% sensitivity, 88.5% PPV, 68.9% NPV, 76.9% diagnostic accuracy, and an AUC value of 0.811, and model 2 showed 80.6% specificity, 84.4% sensitivity, 82.3% PPV, 82.9% NPV, 82.6% diagnostic accuracy, and an AUC value of 0.887. The comparison of AUCs between model1 and model2 was statistically different (P < 0.05). Tuberculosis infection increases the difficulty of discriminating CD from ITB. LASSO regression showed a more efficient ability than Pearson chi-square test based logistic regression on differential diagnosing atypical CD and ITB.

回顾性分析在中南大学湘雅二医院接受阿达木单抗治疗的93例克罗恩病患者的临床和影像学资料，阿达木单抗治疗3个月和1年的总体临床缓解(克罗恩病疾病活动指数<150)率分别为76.3%(71/93)、73.9%(65/88)，1年内镜缓解[克罗恩病内镜严重程度指数(CDEIS)<3]率为31.3%(21/67)。9例单纯小肠型患者中影像学缓解(小肠CT造影肠壁厚度<3 mm且强化基本消退)2例。不良反应发生率为41.9%(39/93)，大部分不良反应轻微可耐受。阿达木单抗治疗3个月实现临床缓解是1年内镜缓解的促成因素[ OR(95%置信区间) 50.220(2.054~1 227.725)， P＝0.016]，小肠+结肠型克罗恩病是1年内镜缓解的促成因素[ OR(95%置信区间) 61.999(1.491~2 578.761)， P＝0.030]；基线CDEIS≥5是1年内镜缓解的不利因素[ OR(95%置信区间) 0.008(0.001~0.123)， P＝0.001]。以上研究结果提示阿达木单抗治疗可有效诱导维持克罗恩病患者临床和内镜缓解，且患者耐受性良好。

Differentiation between Crohn's disease and intestinal tuberculosis is difficult but crucial for medical decisions. This study aims to develop an effective framework to distinguish these two diseases through an explainable machine learning (ML) model. After feature selection, a total of nine variables are extracted, including intestinal surgery, abdominal, bloody stool, PPD, knot, ESAT-6, CFP-10, intestinal dilatation and comb sign. Besides, we compared the predictive performance of the ML methods with traditional statistical methods. This work also provides insights into the ML model's outcome through the SHAP method for the first time. A cohort consisting of 200 patients' data (CD = 160, ITB = 40) is used in training and validating models. Results illustrate that the XGBoost algorithm outperforms other classifiers in terms of area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision and Matthews correlation coefficient (MCC), yielding values of 0.891, 0.813, 0.969, 0.867 and 0.801 respectively. More importantly, the prediction outcomes of XGBoost can be effectively explained through the SHAP method. The proposed framework proves that the effectiveness of distinguishing CD from ITB through interpretable machine learning, which can obtain a global explanation but also an explanation for individual patients.

Background: Exosomes are extensively reported to be strongly associated with many immunologic diseases, including Crohn disease (CD). Meanwhile, the dysfunction of macrophage activation has been proposed to be critical for the pathogenesis of CD. However, it is an unsettled issue whether serum exosomes from CD could activate macrophages and participate in its pathogenesis. Our study intended to clarify the role of CD-derived exosomes on macrophages to elucidate a novel mechanism and possible diagnostic and therapeutic strategies. Methods: Serum exosomes were isolated and identified. Functional assays in vitro were performed on Raw264.7 macrophages, followed by exosomal microRNA (miRNA) profiling and bioinformatics analyses via high-throughput sequencing. In animal experiments, exosomes were intraperitoneally injected into dextran sulfate sodium-induced colitis. Results: In vitro CD-derived exosomes induced proinflammatory cytokine expression and increased macrophage counts. Meanwhile, the intervention of exosomes from CD with epithelial cells led to increased permeability of the intestinal epithelial barrier. In vivo, CD-derived exosomes could circulate into the intestinal mucosa and significantly aggravate colitis. Furthermore, CD changed the miRNA profile of exosomes and further analysis revealed a differential expression of let-7b-5p. Mechanistically, the let-7b-5p/TLR4 pathway was recognized as a potential contributor to macrophage activation and inflammatory response. Furthermore, serum exosome-mediated let-7b-5p mimic delivery alleviated colitis significantly. Conclusions: Our study indicated that serum exosomes can circulate into the intestinal mucosa to aggravate colitis by regulating macrophage activation and epithelial barrier function. In addition, CD showed altered exosomal miRNA profiles. Furthermore, serum exosome-mediated let7b-5p-mimic delivery may significantly alleviate colitis, providing potential novel insight into an exosome-based strategy for the diagnosis and treatment of CD.

Early-life gastrointestinal microbiota development is crucial for physiological development and immunological homeostasis. In the current study, perinatal microbiota and the development of gastrointestinal microbiota in different early-life periods (perinatal, lactation, and postweaning nutrition periods) were explored by using an antibiotic-interfered mouse model and a dextran sulfate sodium-induced colitis mouse model. Gut microbiota samples were collected from mother mice and litters. The results of 16S rRNA gene sequences suggested that microbiota in the gastrointestinal system were present in prenatal fetal mice, and microbiota structures in different parts of the gastrointestinal system of the fetal mice were similar to those in the corresponding gut parts of maternal mice. Microbiota in mucus samples from different regions exhibited higher diversity at birth than at other periods and varied substantially over time with diet change. Moreover, antibiotic treatment in early life affected the composition and diversity of gastrointestinal microbiota in adult mice and enhanced susceptibility to experimental colitis in mice, particularly in the lactation period. This approach of exploring gut microbiota evolution is hoped to provide an enhanced view of how resident microbiota develop in early life, which in turn might facilitate understanding of gut microbiota and related diseases. IMPORTANCE This study investigated resident microbiota in the whole gastrointestinal (GI) tract to explore gut microbiota development in early life and found that early-life antibiotic exposure exacerbated alterations in gut microbiota and murine dextran sulfate sodium (DSS)-induced colitis. Furthermore, the presence of bacteria in the GI tract of mice before birth and the importance of the lactation period in GI microbiota development were confirmed.

Jaundice occurs as a symptom of various diseases, such as hepatitis, the liver cancer, gallbladder or pancreas. Therefore, clinical measurement with special equipment is a common method that is used to identify the total serum bilirubin level in patients. Fully automated multi-class recognition of jaundice combines two key issues: (1) the critical difficulties in multi-class recognition of jaundice approaches contrasting with the binary class and (2) the subtle difficulties in multi-class recognition of jaundice represent extensive individuals variability of high-resolution photos of subjects, huge coherency between healthy controls and occult jaundice, as well as broadly inhomogeneous color distribution. We introduce a novel approach for multi-class recognition of jaundice to detect occult jaundice, obvious jaundice and healthy controls. First, region annotation network is developed and trained to propose eye candidates. Subsequently, an efficient jaundice recognizer is proposed to learn similarities, context, localization features and globalization characteristics on photos of subjects. Finally, both networks are unified by using shared convolutional layer. Evaluation of the structured model in a comparative study resulted in a significant performance boost (categorical accuracy for mean 91.38%) over the independent human observer. Our work was exceeded against the state-of-the-art convolutional neural network (96.85% and 90.06% for training and validation subset, respectively) and showed a remarkable categorical result for mean 95.33% on testing subset. The proposed network makes a performance better than physicians. This work demonstrates the strength of our proposal to help bringing an efficient tool for multi-class recognition of jaundice into clinical practice.

Diagnosis of the esophageal motility disorders is ongoing in clinical evaluations, which is based on traditional method called High-resolution manometry (HRM). However, the huge raw swallow data sets from the HRM are not allowed the doctors to interpret and classify the patients with esophageal symptoms. To this end, modeling propagation between vigor is useful for recognizing esophageal contraction patterns in large-scale high-resolution manometries. In this paper, we learned a discriminative propagation between vigor using deep learning methods. Furthermore, we designed an efficient graph to incorporate contractile vigor propagation (CVP) that considers the contraction and pressure propagation between vigor in HRM images. Using an attention graph convolutional network (GAT), the edges in CVP can automatically learn the contraction patterns (i.e., local temporal information) trends in time series and propagation (i.e., global information) through the attention units. The attention mechanism layer leverages the short-term trend to improve the prediction accuracy. The quantitative experiments showed that the proposed method achieves high accuracy in esophageal contraction pattern recognition and demonstrates its effectiveness compared to existing traditional methods. We also visualized the learned vigor-specific propagation patterns in the contractile features, which show that the proposed CVP-GAT is able to develop interpretable propagation information for esophageal contraction pattern recognition.

•We proposed a novel framework, CHP-Net, to differentiate and localize COVID-19 from community acquired pneumonia.•We used excessive data augmentation to extend the available dataset and optimize the CHP-Net generalization capability.•Comparing to other ConvNet, CHP-Net works much more efficiently to extract feature information on chest X-Ray.•All metrics, including categorical loss, accuracy, precision, recall and F1-score, proved CHP-Net fits good for the task.•CHP-Net are better than the previous methods tested in detecting COVID-19 and exceeding to radiologist.

Subphrenic splenic implantation is a rare disease, usually occurred followed the splenic trauma and splenectomy. Surgeries are often necessary for diagnosing and treating it. A 46-year-old male post-splenectomy patient, tolerating abdominal bloating and pain for more than 1 year, was admitted to the Second Xiangya Hospital, Central South University. Fundus bulge suggested a possibility of stromal tumors originating from the muscularispropria layer with endoscopic ultrasound. Slightly stomachic thickness was detected using enhanced computed tomography (CT). Without any improvement for symptoms after medication, the patient strongly requested to undergo an endoscopic therapy. Natural orifice transluminal endoscopic surgery (NOTES) result confirmed it as subphrenic splenic implantation with postoperative pathology. In this case, NOTES helped us to confirm the diagnosis, relieve the symptoms, as well as prevent secondary surgery injury, which would be helpful to other clinicians.

RATIONALE:Epstein-Barr virus (EBV)-associated T-cell lymphoproliferative disorder (LPD) usually occurs in children and young adults. Gastrointestinal involvement is rare. EBV-associated T-cell lymphoproliferative disorder manifesting as intestinal ulcers poses diagnostic challenges clinically and pathologically because of the atypical manifestations. We concluded that some indicators according to our case and literatures, which might be helpful to the diagnosis of EBV-associated LPD manifested as intestinal ulcers.PATIENT CONCERNS:Here we present a 26-year-old man with complaints of diarrhea and abdominal pain that had persisted for 1 year. Multiform and multifocal deep ulcers were discovered in the colonoscopy. Cell atypia was not obvious but colitis with crypt distortion was found in pathology.DIAGNOSES:According to the symptoms, laboratory examinations, colonoscopy and pathology results, Crohn Disease was diagnosed.INTERVENTIONS:Infliximab therapy was initiated based on the diagnosis of Crohn Disease.OUTCOMES:After the fifth course of therapy, intermittent fever and hematochezia occurred. Physical examination revealed swollen tonsils and ulcers, and purulent exudate from the right tonsil and palatoglossal arch were observed. Biopsies obtained through colonoscopy and nasopharyngoscopy demonstrated EBV-associated T-cell proliferation disease (level 3). After that, the tissue sample from the first colonoscopy was reexamined immunohistochemically. The result suggested EBV-associated T-cell proliferation disease (level 1).LESSONS:When we confront with patients with multiform and multifocal deep intestinal ulcers, not only the common diseases such as Crohn Disease and intestinal tuberculosis should be considered, EBV-associated T-cell proliferation disease should be considered as well. Repeated multiple biopsy, gene rearrangement, EBV DNA quantitative analysis result, EBV-encoded RNA(EBER) and experienced pathologists might be helpful to the diagnosis.

OBJECTIVE:To analyze the clinical features, diagnosis and treatment in patients with immunoglobulin 4 (IgG4)-related diseases.
 Methods: The clinical data (including general situation, clinical manifestations, laboratory examination, imaging examination, pathological examination, treatment and follow-up) in 21 patients, who were diagnosed with IgG4-related diseases in Second Xiangya Hospital of Central South University from June 2014 to February 2018, were retrospectively analyzed.
 Results: Among the 21 patients, including men 16 (76.2%) and women 5 (23.8%), the age was 37.00-78.00 (59.19±12.93) years old. Multi-organ involvement was discovered in 10 patients (47.6%), among which the lung (42.9%), pancreas (38.1%), kidney (33.3%), bile duct (19.0%) and liver (14.3%) were the main organs involved. The serum IgG4 levels in 19 patients (90.5%) were increased [8.63 (1.13-36.50) g/L]. The condition of 16 patients (84.2%) was improved after glucocorticoid therapy.
 Conclusion: IgG4-related diseases are mostly found in middle-aged and elderly men. Multiple organs or tissues of the body can be involved. Affected organs are mostly seen in lung, pancreas, kidney and bile duct, with diverse clinical manifestations. Glucocorticoid and immunosuppressive therapy are effective.

Background Living in a sanitary environment and taking Western-style diet in early life are both risk factors for inflammatory bowel disease and important factors for shaping host gut microbiota. Here, we aimed to establish whether different dietary composition fed during the early period after weaning would associate the susceptibility to DSS-induced colitis with different gut microbiota shifts.Methods Eighty weaned Balb/c mice were fed with high sugar, fat, protein, fiber, and standard diet for 8weeks respectively. Inflammation was induced by administration of 2.5% (wt/vol) dextran sulfate sodium (DSS) in drinking water for 7 days, and the microbiota characterized by 16s rRNA based pyrosequencing. Analyzed the inflammatory factors and toll-like receptors by Real-time PCRResults The high protein and high fiber+protein group exacerbated severity of DSS-induced colitis, the high fiber and high protein+fiber groups had the effect of reducing colitis, and the high sugar, fat and standard group show the similar disease phenotype of colitis. The diversity and richness of the microflora were significantly decreased in the high fiber group, while only decreased richness of flora was observed in the high protein group. The abundance of Firmicutes was decreased and the abundance of Bacteroides was increased in the high fat, high sugar, high protein and high fiber groups, especially in the high protein and high fiber group. The microbial community structure was slightly different at the species/genus level. The microbial community structure of high protein-fiber group and high fiber-protein group was still similar.Conclusions Mice were fed with different dietary compositions of high sugar, fat, protein and fiber diets since weaning, and similar gut microbiota of high-abundance Bacteroides and low-abundance Firmicutes are formed in adult mice. These microbiota do not cause colonic mucosal damage directly. Only high protein diet aggravated DSS-induced colitis, while high fiber diet alleviated the colitis.

BackgroundThe differentiation between untypical intestinal tuberculosis (UITB) and untypical Crohn's disease (UCD) is a challenge.AimsTo analyze phenotypic variables and propose a novel prediction model for differential diagnosis of two conditions.MethodsA total of 192 patients were prospectively enrolled. The clinical, laboratory, endoscopic, and radiological features were investigated and subjected to univariable and multivariable analyses. The final prediction model for differentiation between UCD and UITB was developed by logistic regression analysis and Fisher discriminant analysis on the training set. The same discriminant function was tested on the validation set.ResultsTwenty-five candidates were selected from 52 phenotypic variables of typical Crohn's disease (TCD), UCD, and UITB patients. UCD's variables overlapped with both TCD and UITB. The percentages of tuberculosis history, positive PPD, and positive T-SPOT result in UCD were all significantly higher than that in TCD (11.6% vs. 0.0%, 27.9% vs. 0.0%, 25.6% vs. 4.5%, respectively, P<0.05). The regression equations and Fisher discriminant function for discrimination between UCD and UITB were developed. In the training data, the area under the receiver operating characteristic of equations was 0.834, 0.69, and 0.648 in the clinical-laboratory, endoscopic, and radiological model, respectively. The accuracy of Fisher discriminant function for discrimination was 86% in UCD and 73% in UITB in the validation data.ConclusionsPhenotypes of UCD patients in TB-endemic countries may be associated with TB infection history. Fisher discriminant analysis is a good choice to differentiate UCD from UITB, which is worthy of verification in clinical practice.

The internal environment of the gallbladder has been considered extremely unfavorable for bacterial growth, and the microbial profile of the gallbladder still unknown. By high-throughput sequencing of the bacterial 16S rRNA gene, we studied the microbial profile of the gallbladder from healthy rabbits before and after weaning. Moreover, we investigated the difference of microbiota between the gallbladder and gut. Our results showed that the gallbladder was dominantly populated by Firmicutes, Bacteroidetes, Proteobacteria, and Actinobacteria in the phylum throughout the developmental stages of rabbits. The adult rabbits showed higher species richness and exhibited higher bacterial diversity than rabbits before weaning based on the results of alpha diversity. Beta diversity analyses indicated differences in the bacterial community composition between different developmental stages. In the comparison of the gallbladder and feces, Firmicutes and Bacteroidetes were dominant in the phylum, as they were present in about 61% and 21% of the feces, respectively. Conversely, in the gallbladder, Firmicutes was the most dominant (about 41%), and Bacteroidetes and Proteobacteria were present in about 16% and 22% of the gallbladder, respectively. The Unweighted UniFrac Principal Coordinate Analysis results illustrated samples clustered into 2 categories: the gallbladder and feces. Our study might provide a foundation for knowledge on gallbladder microbiota for the first time and a basis for further studies on gallbladder and intestinal health.

While the microbial community of the small intestine mucus (SIM) may also play a role in human health maintenance and disease genesis, it has not been extensively profiled and whether it changes with diet is still unclear. To investigate the flora composition of SIM and the effects of diet on it, we fed SD rats for 12 weeks with standard diet (STD), high-fat diet (HFD), high-sugar diet (HSD) and high-protein diet (HPD), respectively. After 12 weeks, the rats were sacrificed, SIM and stool samples were collected, and high-throughput 16S rRNA gene sequencing was used to analyze the microbiota. We found that fecal microbiota (FM) was dominated by Firmicutes and Bacteroidetes, while in SIM, Firmicutes and Proteobacteria were the two most abundant phyla and the level of Bacteroidetes dramatically decreased. The microbiota diversity of SIM was less than that of feces. The community composition of SIM varied greatly with different diets, while the composition of FM altered little with different diets. The relative abundance of Bacteroidetes and Allobaculum in SIM were negatively correlated with weight gain. There was no significant correlation between FM and weight gain. In conclusion, the community profile of SIM is different from that of feces and susceptible to diet.

【目的】探讨冠心病患者消化道出血后远期发生心血管不良事件的危险因素及AIMS65、Glasgow-Blatchford（GBS）评分系统预测远期心血管不良事件的能力。【方法】回顾性分析2014年至2016年于湘雅二医院住院的冠心病合并消化道出血病人的临床资料，根据随访时是否发生心血管不良事件分组，分析两组的临床特点、发生终点事件的危险因素及评估两种评分预测效能。【结果】219例病人中，70人（31.9%）发生心血管不良事件，AIMS65及GBS评分系统预测心血管不良事件的ROC分别为0.59（P=0.035）及0.51（P=0.039），单因素分析中年龄、糖尿病、既往心梗、血红蛋白浓度、住院期间是否使用PPI、输血有意义（P<0.05），经多因素分析后血红蛋白浓度、糖尿病病史、心梗病史有统计学意义。【结论】现有的GBS评分系统及AIMS评分系统对冠心病合并消化道出血患者的远期预后的预测功能一般，并且贫血、高血压、糖尿病是这部分病人心血管不良事件发生的独立危险因素。