Artificial intelligence in inflammatory bowel disease: implications for clinical practice and future directions

Inflammatory bowel disease encompasses Crohn’s disease and ulcerative colitis and is characterized by uncontrolled, relapsing, and remitting course of inflammation in the gastrointestinal tract. Artificial intelligence represents a new era within the field of gastroenterology, and the amount of research surrounding artificial intelligence in patients with inflammatory bowel disease is on the rise. As clinical trial outcomes and treatment targets evolve in inflammatory bowel disease, artificial intelligence may prove as a valuable tool for providing accurate, consistent, and reproducible evaluations of endoscopic appearance and histologic activity, thereby optimizing the diagnosis process and identifying disease severity. Furthermore, as the applications of artificial intelligence for inflammatory bowel disease continue to expand, they may present an ideal opportunity for improving disease management by predicting treatment response to biologic therapies and for refining the standard of care by setting the basis for future treatment personalization and cost reduction. The purpose of this review is to provide an overview of the unmet needs in the management of inflammatory bowel disease in clinical practice and how artificial intelligence tools can address these gaps to transform patient care.

A multi-centre prospective study of COVID-19 transmission following outpatient Gastrointestinal Endoscopy in the United Kingdom

MessageThe COVID-19 pandemic has severely curtailed the practice of endoscopy (as an exemplar for outpatient diagnostic procedures) worldwide. Restart and recovery processes will be influenced by the need to protect patients and staff from disease transmission, but data on the risk of COVID-19 transmission after endoscopy are sparse. This is of particular importance in later pandemic phases when the risk of harm from delayed or missed significant diagnoses is likely to far outweigh the risk of infection. The British Society of Gastroenterology (BSG) guidance for restarting endoscopy included stratification of diagnostic procedures according to aerosol generation or assessment of infectious risk as well as pragmatic guidance on the use of personal protective equipment (PPE). We sought to document the risk of COVID-19 transmission after endoscopy in this "COVID-minimised" environment. Prospective data were collected from 18 UK centres for n=6208 procedures. Pre-endoscopy, 3/2611 (0.11% [95% CI: 0.00-0.33%]) asymptomatic patients tested positive for SARS-CoV-2 on nasopharyngeal swab. Based on follow-up telephone symptom screening of patients at 7 and 14 days, no cases of COVID-19 were detected by any centre after endoscopy in either patients or staff. While these data cannot determine the relative contribution of each component of a COVID-minimised pathway, they provide clear support for such an approach. The rational use of PPE and infection control policies should be continued and will aid planning for outpatient diagnostics in the COVID-19 recovery phase.

Optimal Endoscopic Treatment and Surveillance of Serrated Polyps

Serrated polyps are considered precursor lesions that account for 15% to 30% of colorectal cancers, and they are overrepresented as a cause of interval cancers. They are difficult to detect and resect comprehensively; however, recent data suggest that high definition endoscopy, chromoendoscopy (via spray catheter, pump or orally), narrow band imaging, split-dose bowel preparation and a slower withdrawal (>6 minutes) can all improve detection. Cold snare resection is effective and safe for these lesions, including cold snare piecemeal endoscopic mucosal resection, which is likely to become the standard of care for lesions >10 mm in size. Sessile serrated lesions ≥10 mm in size, those exhbiting dysplasia, or traditional serrated adenomas increase the chance of future advanced neoplasia. Thus, a consensus is emerging: a surveillance examination at 3 years should be recommended if these lesions are detected. Serrated lesions likely carry equivalent risk to adenomas, so future guidelines may consider serrated class lesions and adenomas together for risk stratification. Patients with serrated polyposis syndrome should undergo surveillance every 1 to 2 years once the colon is cleared of larger lesions, and their first degree relatives should undergo screening every 5 years starting at age 40.

Principles of Quality Controlled Endoscopic Submucosal Dissection with Appropriate Dissection Level and High Quality Resected Specimen

Endoscopic submucosal dissection (ESD) has enabled en bloc resection of early stage gastrointestinal tumors with negligible risk of lymph node metastasis, regardless of tumor size, location, and shape. However, ESD is a relatively difficult technique compared with conventional endoscopic mucosal resection, requiring a longer procedure time and potentially causing more complications. For safe and reproducible procedure of ESD, the appropriate dissection of the ramified vascular network in the level of middle submucosal layer is required to reach the avascular stratum just above the muscle layer. The horizontal approach to maintain the appropriate depth for dissection beneath the vascular network enables treatment of difficult cases with large vessels and severe fibrosis. The most important aspect of ESD is the precise evaluation of curability. This approach can also secure the quality of the resected specimen with enough depth of the submucosal layer.

Colonoscopic Cancer Surveillance in Inflammatory Bowel Disease: What's New Beyond Random Biopsy?

Colonoscopy based colitis surveillance is widely accepted to try to prevent development of and ensure early detection of colitis-associated colorectal cancer. Traditionally this has been performed with quadrantic random biopsies throughout the colon. Chromoendoscopy "dye-spray" with targeted biopsies only has been shown to increase dysplasia detection 4 to 5 fold on a per lesion basis. It has therefore been suggested that random biopsies should be abandoned as they do not increase dysplasia detection nor change patient clinical course. Recent British guidelines for colitis surveillance have strongly endorsed chromoendoscopy. This short review summarizes current international guidelines and looks at how to optimize white light colonoscopy in colitis considering: bowel preparation, withdrawal time, high definition, and structure enhancement. Data for advanced imaging techniques are reviewed including positive evidence in favor of chromoendoscopy, and limited data suggesting autofluoresence imaging may be promising. Narrow band imaging does not increase dysplasia detection in colitis. Confocal endomicroscopy might potentially reduce biopsies beyond that of chromoendoscopy but does not offer a clear detection advantage. Pan-colonic chromoendoscopy with targeted biopsies increases dysplasia detection and is the standard of care in the United Kingdom. It is likely that the use of chromoendoscopy for colitis surveillance will become widely accepted internationally.