Development and application of an artificial intelligence-assisted endoscopy system for diagnosis of Helicobacter pylori infection: a multicenter randomized controlled study.

BACKGROUND: The early diagnosis and treatment of Heliobacter pylori (H.pylori) gastrointestinal infection provide significant benefits to patients. We constructed a convolutional neural network (CNN) model based on an endoscopic system to diagnose H. pylori infection, and then examined the potential benefit of this model to endoscopists in their diagnosis of H. pylori infection. MATERIALS AND METHODS: A CNN neural network system for endoscopic diagnosis of H.pylori infection was established by collecting 7377 endoscopic images from 639 patients. The accuracy, sensitivity, and specificity were determined. Then, a randomized controlled study was used to compare the accuracy of diagnosis of H. pylori infection by endoscopists who were assisted or unassisted by this CNN model. RESULTS: The deep CNN model for diagnosis of H. pylori infection had an accuracy of 89.6%, a sensitivity of 90.9%, and a specificity of 88.9%. Relative to the group of endoscopists unassisted by AI, the AI-assisted group had better accuracy (92.8% [194/209; 95%CI: 89.3%, 96.4%] vs. 75.6% [158/209; 95%CI: 69.7%, 81.5%]), sensitivity (91.8% [67/73; 95%CI: 85.3%, 98.2%] vs. 78.6% [44/56; 95%CI: 67.5%, 89.7%]), and specificity (93.4% [127/136; 95%CI: 89.2%, 97.6%] vs. 74.5% [114/153; 95%CI: 67.5%, 81.5%]). All of these differences were statistically significant (P < 0.05). CONCLUSION: Our AI-assisted system for diagnosis of H. pylori infection has significant ability for diagnostic, and can improve the accuracy of endoscopists in gastroscopic diagnosis. TRIAL REGISTRATION: This study was approved by the Ethics Committee of Daping Hospital (10/07/2020) (No.89,2020) and was registered with the Chinese Clinical Trial Registration Center (02/09/2020)   ( www.chictr.org.cn ; registration number: ChiCTR2000037801).

ZO-1 and IL-1RAP Phosphorylation: Potential Role in Mediated Brain-Gut Axis Dysregulation in Irritable Bowel Syndrome-like Stressed Mice.

Background and Objectives: Irritable Bowel Syndrome (IBS) is a common gastrointestinal disorder often exacerbated by stress, influencing the brain-gut axis (BGA). BGA dysregulation, disrupted intestinal barrier function, altered visceral sensitivity and immune imbalance defects underlying IBS pathogenesis have been emphasized in recent investigations. Phosphoproteomics reveals unique phosphorylation details resulting from environmental stress. Here, we employ phosphoproteomics to explore the molecular mechanisms underlying IBS-like symptoms, mainly focusing on the role of ZO-1 and IL-1RAP phosphorylation. Materials and Methods: Morris water maze (MWM) was used to evaluate memory function for single prolonged stress (SPS). To assess visceral hypersensitivity of IBS-like symptoms, use the Abdominal withdrawal reflex (AWR). Colonic bead expulsion and defecation were used to determine fecal characteristics of the IBS-like symptoms. Then, we applied a phosphoproteomic approach to BGA research to discover the molecular mechanisms underlying the process of visceral hypersensitivity in IBS-like mice following SPS. ZO-1, p-S179-ZO1, IL-1RAP, p-S566-IL-1RAP and GFAP levels in BGA were measured by western blotting, immunofluorescence staining, and enzyme-linked immunosorbent assay to validate phosphorylation quantification. Fluorescein isothiocyanate-dextran 4000 and electron-microscopy were performed to observe the structure and function of the intestinal epithelial barrier. Results: The SPS group showed changes in learning and memory ability. SPS exposure affects visceral hypersensitivity, increased fecal water content, and significant diarrheal symptoms. Phosphoproteomic analysis displayed that p-S179-ZO1 and p-S566-IL-1RAP were significantly differentially expressed following SPS. In addition, p-S179-ZO1 was reduced in mice's DRG, colon, small intestine, spinal and hippocampus and intestinal epithelial permeability was increased. GFAP, IL-1ß and p-S566-IL-1RAP were also increased at the same levels in the BGA. And IL-1ß showed no significant difference was observed in serum. Our findings reveal substantial alterations in ZO-1 and IL-1RAP phosphorylation, correlating with increased epithelial permeability and immune imbalance. Conclusions: Overall, decreased p-S179-ZO1 and increased p-S566-IL-1RAP on the BGA result in changes to tight junction structure, compromising the structure and function of the intestinal epithelial barrier and exacerbating immune imbalance in IBS-like stressed mice.

Prediction of Esophageal Stricture after Endoscopic Submucosal Dissection in Patients with Early Esophageal Cancer.

BACKGROUND: Endoscopic submucosal dissection (ESD) treatment of early esophageal cancer is effective and safe. It is currently the first-line treatment for early esophageal cancer. However, a common side effect is the development of esophageal strictures after ESD. This study was designed to identify the risk factors for esophageal stricture development and to predict its occurrence after ESD. METHODS: In this retrospective study, 150 consecutive patients with early esophageal cancer treated with ESD at Daping Hospital, Chongqing, were enrolled between January 2016 and December 2020. Data on patient demographics, esophageal tumor characteristics, procedure-related factors, and postoperative situations were collected. We identified independent risk factors of esophageal stricture formation using univariate analysis and multivariate logistic regression. The predictive probability was obtained after multivariate logistic analysis. In addition, patients were divided into six groups based on these risk factors and the rate of esophageal stricture in each group was analyzed. RESULTS: The postoperative esophageal stricture rate was 14% (21/150). Tumor location (OR = 5.655, 95% CI: 1.245-25.691, P = 0.025) and circumferential resection range (OR = 16.113, 95% CI: 4.294-60.466, P < 0.001) are independent risk factors for the development of esophageal strictures. According to predictive probability analysis and the rates of stricture in six groups, we developed a possible flow chart to predict stricture formation. CONCLUSIONS: Tumor location and circumferential resection range are reliable risk factors to predict the occurrence of esophageal strictures. Our prediction flow chart suggests that tumors with a circumferential resection range of 1/2-3/4 and located above the upper thoracic segment or a circumferential resection range of > 3/4 have a high risk of postoperative stricture. Thus, timely and effective preventive measures should be taken in these patients following ESD.

High dose PPI-amoxicillin dual therapy for the treatment of Helicobacter pylori infection: a systematic review with meta-analysis.

BACKGROUND: Helicobacter pylori resistance to amoxicillin remains rare in many regions. Proton pump inhibitor-amoxicillin-containing high dose dual therapy (HDDT) has been proposed to treat H. pylori infection. We aimed to assess the effectiveness and safety of PPI-amoxicillin HDDT for treatment of H. pylori infection in comparison with other regimens. METHODS: Databases, including PubMed, Embase, and the Cochrane Register of Controlled Trials, were searched to find relevant publications. Randomized controlled trials comparing HDDT with control regimens for H. pylori eradication in adult patients were included. The primary outcome was eradication rate by intention-to-treat analysis. Adverse events were analyzed as second outcome. RESULTS: A total of 15 trials with 3818 patients qualified for inclusion. The eradication rate of HDDT was neither significantly inferior nor superior to the recommended regimens such as triple therapy, bismuth quadruple therapy, and non-bismuth quadruple therapy [relative risk (RR): 1.00, 95% confidence interval (CI): 0.96-1.05, p = 0.870]. This finding was robust through subgroup analyses and sensitivity analyses. Trial sequential analysis showed that HDDT was equivalent to control regimens, and further similar trials were unlikely to alter the conclusions of this analysis. The frequency of adverse events was significantly lower in HDDT group (RR: 0.48, 95% CI: 0.37-0.64, p < 0.001). CONCLUSION: HDDT was equivalent to recommended first-line or rescue regimens with fewer adverse effects. The evidence from this meta-analysis supports the use of HDDT as first-line or rescue treatment for H. pylori infection. TRIAL REGISTRATION: PROSPERO CRD42019133002.

Comparison of Polyethylene Glycol versus Lactulose Oral Solution for Bowel Preparation prior to Colonoscopy.

OBJECTIVE: This study was conducted to compare a lactulose oral solution with a polyethylene glycol (PEG) formulation for colonoscopy preparation using the following metrics: quality of cleansing, colonoscopy outcomes, patient/physician satisfaction, and patient tolerability. METHODS: The enrolled patients were randomly divided into two groups and received a single 2 L dose of either PEG (PEG group) or lactulose (Lac group). The Boston Bowel Preparation Scale (BBPS) was used for assessing the cleansing quality of the bowel preparations. Patient tolerability and adverse events were obtained through the completion of questionnaires. RESULTS: The lactulose oral solution showed superior bowel cleansing compared to PEG, as evidenced by higher BBPS scores in the Lac group for all segments of the colon (P < 0.05). The detection rates of polyps and intestinal lesions in the Lac group (30.68% and 36.36%, respectively) were significantly higher than those in the PEG group (12.50% vs. 13.63%, respectively). For the degree of satisfaction, the Lac group had significantly higher scores compared to the PEG group, as evaluated by both the patients and endoscopist. PEG was associated with an increased incidence of nausea. There were no statistical differences between the groups in terms of vomiting, abdominal pain or fullness, dizziness, unfavorable palatability, dry mouth, palpitation, tinnitus, and tongue numbness. CONCLUSION: A single 2 L dose of a lactulose oral solution had higher efficacy, improved tolerability, and acceptable safety for bowel preparation when compared to the same volume of PEG. Thus, a lactulose oral solution may be a potential bowel-cleansing option for colonoscopy preparation.