Introduction: Microscopic colitis is a chronic inflammatory bowel disease characterised by normal or almost normal endoscopic appearance of the colon, chronic watery, nonbloody diarrhoea and distinct histological abnormalities, which identify three histological subtypes, the collagenous colitis, the lymphocytic colitis and the incomplete microscopic colitis. With ongoing uncertainties and new developments in the clinical management of microscopic colitis, there is a need for evidence‐based guidelines to improve the medical care of patients suffering from this disorder.Methods: Guidelines were developed by members from the European Microscopic Colitis Group and United European Gastroenterology in accordance with the Appraisal of Guidelines for Research and Evaluation II instrument. Following a systematic literature review, the Grading of Recommendations Assessment, Development and Evaluation methodology was used to assess the certainty of the evidence. Statements and recommendations were developed by working groups consisting of gastroenterologists, pathologists and basic scientists, and voted upon using the Delphi method.Results: These guidelines provide information on epidemiology and risk factors of microscopic colitis, as well as evidence‐based statements and recommendations on diagnostic criteria and treatment options, including oral budesonide, bile acid binders, immunomodulators and biologics. Recommendations on the clinical management of microscopic colitis are provided based on evidence, expert opinion and best clinical practice.Conclusion: These guidelines may support clinicians worldwide to improve the clinical management of patients with microscopic colitis.

Distinction between Crohn’s disease of the colon-rectum and ulcerative colitis or inflammatory bowel disease (IBD) type unclassified can be of pivotal importance for a tailored clinical management, as each entity often involves specific therapeutic strategies and prognosis. Nonetheless, no gold standard is available and the uncertainty of diagnosis may frequently lead to misclassification or repeated examinations. Hence, we have performed a literature search to address the problem of differential diagnosis in IBD colitis, revised current and emerging diagnostic tools and refined disease classification strategies. Nowadays, the differential diagnosis is an untangled issue, and the proper diagnosis cannot be reached in up to 10% of patients presenting with IBD colitis. This topic is receiving emerging attention, as medical therapies, surgical approaches and leading prognostic outcomes require more and more disease-specific strategies in IBD patients. The optimization of standard diagnostic approaches based on clinical features, biomarkers, radiology, endoscopy and histopathology appears to provide only marginal benefits. Conversely, emerging diagnostic techniques in the field of gastrointestinal endoscopy, molecular pathology, genetics, epigenetics, metabolomics and proteomics have already shown promising results. Novel advanced endoscopic imaging techniques and biomarkers can shed new light for the differential diagnosis of IBD, better reflecting diverse disease behaviors based on specific pathogenic pathways.

Background and aims Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE. Methods Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers. Results The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %). Conclusion MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential. ^* KID working group