Clinical trials

This study aims to develop, validate and evaluate an artificial intelligence-based system for real-time automatic localization of colorectal anatomical sites during colonoscopy and detection of colonoscopic inspection extent, so as to improve examination quality and the precision of lesion management. The hypothesis of this study is that a colonoscopic image recognition model built on deep convolutional neural networks can accurately extract intestinal anatomical features from endoscopic video frames. In prospective and retrospective independent validation cohorts, the artificial intelligence model is hypothesized to achieve an overall accuracy of no less than 85% for the multi-class anatomical site localization task across colonic segments, with an expected sensitivity of 90% and specificity of 85%. The model predictions are expected to be in high agreement with assessments by senior endoscopists, with an anticipated Kappa coefficient of 0.80. This will verify the technical feasibility and accuracy of deep learning-driven real-time anatomical localization during colonoscopy.

The purpose of this study is to propose a non-invasive screening method by integrating holographic biological theory and artificial intelligence technology. A colorectal cancer risk assessment model will be constructed by analyzing multimodal data including facial features, tongue image characteristics and exhaled gas. The hypothesis of this study is that the model can attain both sensitivity and specificity of 80%.This study will enroll patients aged 18-80 years scheduled to undergo colonoscopy. All participants shall provide informed consent and sign the informed consent form. Patients will be excluded if they have severe cardiac, cerebral, pulmonary or renal dysfunction, or psychiatric disorders precluding colonoscopy, have a history of gastrointestinal surgery, or have taken bismuth agents or other staining medications. Based on estimates from existing literature, the training set will require tongue images, facial images, exhaled gas analysis results and colonoscopic diagnoses from 5000 patients, and the test set will require such data from 6000 patients.

Abdominal bloating is a common clinical symptom in the digestive system, with obscure origins and complex mechanisms. Its etiology can be attributed to organic diseases and various Functional Gastrointestinal Disorders (FGIDs). In recent years, the roles of Small Intestinal Bacterial Overgrowth (SIBO), Oral-Cecal Transit Time (OCTT), and gut microbiota dysbiosis in Functional Abdominal Bloating/Distention (FAB/D) have garnered increasing attention. Currently, there is a lack of diagnostic tests and effective treatment measures for patients with bloating. The hydrogen/methane breath test is a safe, economical, and non-invasive examination recommended for diagnosing SIBO. Rifaximin, an antibiotic that acts exclusively in the intestines, has been widely validated for its efficacy in SIBO and in patients with SIBO co-occurring with Irritable Bowel Syndrome (IBS). However, research on the role of SIBO in the production of bloating symptoms and the extent to which rifaximin treatment of SIBO alleviates symptoms in clinical bloating patients is still lacking. This study aims to investigate the efficacy of rifaximin in patients with SIBO who primarily present with bloating. Exploring clinical treatment options for bloating provides a reference for its management. Furthermore, questionnaires on psychiatric symptoms and fecal microbiota analysis for patients with bloating-type SIBO can help clarify the etiology of bloating, offering a basis for the etiological treatment of bloating patients in the next steps.

The aim of this observational study was to understand the effect of radiofrequency ablation on subjects with moderate to severe gastric atrophy with enterocolitis with or without low-grade intraepithelial neoplasia who underwent radiofrequency ablation. The main question it aims to answer is: Does radiofrequency ablation therapy reduce gastric mucosal atrophy and enterosis in subjects with moderate to severe gastric atrophy with enterosis with or without low-grade intraepithelial neoplasia?

Helicobacter pylori (H. pylori) infection, a prevalent global infectious disease, is a significant contributor to gastric cancer and other morbidities, imposing a substantial disease burden. With the rise in antibiotic resistance, the eradication of H. pylori is encountering formidable challenges. A subset of individuals, despite undergoing multiple treatment regimens, remain unable to successfully eradicate the infection. The persistence of infection in these cases could be attributed to either the limitations of detection methods leading to false positives or to the infection by superbugs that are highly resistant to antibiotics. This study is designed to ascertain whether these patients are infected with superbugs by employing various diagnostic techniques. Additionally, it aims to assess the antibiotic resistance profiles of strains associated with extremely refractory H. pylori infections through drug susceptibility testing. Based on the identified sensitivities, the study seeks to tailor treatment protocols with bismuth-containing quadruple therapy (Containing two kinds of antibiotics: sensitive antibiotic, rifabutin or high-dose metronidazole), to explore novel therapeutic strategies for patients with highly resistant H. pylori infections.