A multisystem-compatible deep learning-based algorithm for detection and characterization of angiectasias in small-bowel capsule endoscopy. A proof-of-concept study.

BACKGROUND AND AIMS: Current artificial intelligence (AI)-based solutions for capsule endoscopy (CE) interpretation are proprietary. We aimed to evaluate an AI solution trained on a specific CE system (Pillcam®, Medtronic) for the detection of angiectasias on images captured by a different proprietary system (MiroCam®, Intromedic). MATERIAL AND METHODS: An advanced AI solution (Axaro®, Augmented Endoscopy), previously trained on Pillcam® small bowell images, was evaluated on independent datasets with more than 1200 Pillcam® and MiroCam® still frames (equally distributed, with or without angiectasias). Images were reviewed by experts before and after AI interpretation. RESULTS: Sensitivity for the diagnosis of angiectasia was 97.4% with Pillcam® images and 96.1% with Mirocam® images, with specificity of 98.8% and 97.8%, respectively. Performances regarding the delineation of regions of interest and the characterization of angiectasias were similar in both groups (all above 95%). Processing time was significantly shorter with Mirocam® (20.7 ms) than with Pillcam® images (24.6 ms, p<0.0001), possibly related to technical differences between systems. CONCLUSION: This proof-of-concept study on still images paves the way for the development of resource-sparing, "universal" CE databases and AI solutions for CE interpretation.

Granulocyte/monocyte adsorptive apheresis for the treatment of therapy-refractory chronic active ulcerative colitis.

OBJECTIVES: Current options for patients with steroid-dependent, chronic-active ulcerative colitis (UC) with insufficient response/intolerance to immunosuppressants (ISs) and/or biologics are limited. The aim of this study was to assess the long-term outcome of granulocyte/monocyte adsorptive (GMA) apheresis (Adacolumn®) in this population. MATERIALS AND METHODS: Ninety five adults with steroid-dependent active UC and insufficient response/intolerance to IS and/or TNF inhibitors received 5-8 aphereses in a single induction series of ≤10 weeks. Endpoints included rates of remission (clinical activity index [CAI] ≤ 4) at weeks 24 and 48. RESULTS: Of 94 patients (ITT population), remission and response rates were 34.0% and 44.7% at week 24, and 33.0% and 39.4% at week 48. Among 30 patients with prior failure of IS and biologics, 33.3% and 20.0% were in remission at weeks 24 and 48. At both weeks, 19.2% of patients achieved steroid-free remission. Sustained remission or response occurred in 27.7% of patients at 48 weeks. The cumulative colectomy rate at week 96 was 23.4%. Safety was consistent with previous findings. CONCLUSIONS: This study confirms findings of the 12-week interim analysis and demonstrates that GMA apheresis provides a safe and beneficial long-term outcome for patients with chronic active UC resistant/intolerant to IS and/or TNF inhibitors.

International core curriculum for capsule endoscopy training courses.

Capsule endoscopy (CE) has become a first-line noninvasive tool for visualisation of the small bowel (SB) and is being increasingly used for investigation of the colon. The European Society of Gastrointestinal Endoscopy (ESGE) guidelines have specified requirements for the clinical applications of CE. However, there are no standardized recommendations yet for CE training courses in Europe. The following suggestions in this curriculum are based on the experience of European CE training courses directors. It is suggested that 12 hours be dedicated for either a small bowel capsule endoscopy (SBCE) or a colon capsule endoscopy (CCE) course with 4 hours for an introductory CCE course delivered in conjunction with SBCE courses. SBCE courses should include state-of-the-art lectures on indications, contraindications, complications, patient management and hardware and software use. Procedural issues require approximately 2 hours. For CCE courses 2.5 hours for theoretical lessons and 3.5 hours for procedural issued are considered appropriate. Hands-on training on reading and interpretation of CE cases using a personal computer (PC) for 1 or 2 delegates is recommended for both SBCE and CCE courses. A total of 6 hours hands-on session- time should be allocated. Cases in a SBCE course should cover SB bleeding, inflammatory bowel diseases (IBD), tumors and variants of normal and cases with various types of polyps covered in CCE courses. Standardization of the description of findings and generation of high-quality reports should be essential parts of the training. Courses should be followed by an assessment of trainees' skills in order to certify readers' competency.

Successful use of adalimumab in patient with treatment-refractory microscopic colitis.

A 50-year-old woman with treatment-refractory lymphocytic colitis was diagnosed with ankylosing spondylitis. She was started on adalimumab injections which significantly improved her stool frequency and consistency and, consequently, her quality of life.

Association Between Fecal Calprotectin Levels and Small-bowel Inflammation Score in Capsule Endoscopy: A Multicenter Retrospective Study.

BACKGROUND: Accurate inflammation reporting in capsule endoscopy (CE) is important for diagnosis and monitoring of treatment of inflammatory bowel disease (IBD). Fecal calprotectin (FC) is a highly specific biomarker of gut inflammation. Lewis score (LS) was developed to standardize quantification of inflammation in small-bowel (SB) CE images. GOALS: Multicenter retrospective study aiming to investigate correlation between LS and FC in a large group of patients undergoing CE for suspected or known small-bowel IBD, and to develop a model for prediction of CE results (LS) based on FC levels. STUDY: Five academic centers and a district general hospital offering CE in UK, Finland, Sweden, Canada, and Israel. In total, 333 patients were recruited. They had small-bowel CE and FC done within 3 months. RESULTS: Overall, correlation between FC and LS was weak (r s: 0.232, P < 0.001). When two clinically significant FC thresholds (100 and 250 µg/g) were examined, the r s between FC and LS was 0.247 (weak) and 0.337 (moderate), respectively (P = 0.307). For clinically significant (LS ≥ 135) or negative (LS < 135) for SB inflammation, ROC curves gave an optimum cutoff point of FC 76 µg/g with sensitivity 0.59 and specificity 0.41. LIMITATIONS: Retrospective design. CONCLUSIONS: LS appears to show low correlation with FC as well as other serology markers of inflammation. FC does not appear to be a reliable biomarker for significant small-bowel inflammation. Nevertheless, FC level ≥ 76 µg/g may be associated with appreciable visual inflammation on small-bowel CE in patients with negative prior diagnostic workup.

Safety and Efficacy of Granulocyte/Monocyte Apheresis in Steroid-Dependent Active Ulcerative Colitis with Insufficient Response or Intolerance to Immunosuppressants and/or Biologics [the ART Trial]: 12-week Interim Results.

BACKGROUND AND AIMS: Patients with active, steroid-dependent ulcerative colitis with insufficient response or intolerance to immunosuppressants and/or biologic therapies have limited treatment options. Adacolumn, a granulocyte/monocyte adsorptive apheresis device, has shown clinical benefit in these patients. This study aimed to provide additional clinical data regarding the safety and efficacy of Adacolumn in this patient subgroup. METHODS: This single-arm, open-label, multicentre trial [ART] was conducted at 18 centres across the UK, France, and Germany. Eligible patients were 18-75 years old with moderate-to-severe, steroid-dependent active ulcerative colitis with insufficient response or intolerance to immunosuppressants and/or biologics. Patients received ≥ 5 weekly apheresis sessions with Adacolumn. The primary endpoint was clinical remission rate [clinical activity index ≤ 4] at Week 12. RESULTS: In all, 86 patients were enrolled. At Week 12, 33/84 [39.3%] of patients in the intention-to-treat population achieved clinical remission, with 47/84 [56.0%] achieving a clinical response [clinical activity index reduction of ≥ 3]. Clinical remission was achieved in 30.0% of patients with previous immunosuppressant and biologic failure; steroid-free clinical remission and response were observed in 22.6% and 35.7% of these patients, respectively. Quality of life [Short Health Scale] significantly improved at Week 12 [p < 0.0001]. The majority of adverse events were of mild/moderate intensity. CONCLUSIONS: At Week 12, Adacolumn provided significant clinical benefit in a large cohort of steroid-dependent ulcerative colitis patients with previous failure to immunosuppressant and/or biologic treatment, with a favourable safety profile. These results are consistent with previous studies and support Adacolumn use in this difficult-to-treat patient subgroup.

Small bowel capsule endoscopy in the management of established Crohn's disease: clinical impact, safety, and correlation with inflammatory biomarkers.

BACKGROUND: Multiple studies have established the superior diagnostic accuracy of video capsule endoscopy (VCE) for the diagnosis of small bowel (SB) Crohn's disease (CD). However, data on the clinical impact of VCE in patients with established CD are scarce. The aim of this study was to examine the impact and safety of VCE on the clinical management of patients with established CD. METHODS: A retrospective, multicenter, cross-sectional study. The study cohort included consecutive patients with established SB CD who underwent VCE in 4 tertiary referral centers (1 Canada, 1 Sweden, and 2 United Kingdom) from January 2008 to October 2013. Patients were excluded if VCE was performed as a part of the initial diagnostic workup. The presence of SB mucosal inflammation was quantified using the Lewis score. Inflammatory biomarkers (C-reactive protein and fecal calprotectin) were measured and correlated with the Lewis score. RESULTS: The study included 187 patients. No SB inflammation was observed in 28.4%, mild-to-moderate inflammation in 26.6%, and moderate-to-severe inflammation in 45% of the patients (median Lewis score, 662; range, 0-6400). A change in management was recommended in 52.3% of the patients based on VCE findings. Elevated C-reactive protein, fecal calprotectin, or the combination of both were poorly correlated with significant SB inflammation. SB capsule retention occurred in 4 patients (2.1%). CONCLUSIONS: VCE in patients with established CD is safe, and the results often have a significant clinical impact. VCE should not be limited to CD patients with positive inflammatory markers because their predictive value for significant SB inflammation is poor.

First successful use of leukocyte apheresis as maintenance therapy for Crohn's disease in the United Kingdom.

We describe the case of a 24 year old male with severe fistulating Crohn's disease who failed mutliple modalities of medical and surgical therapy. We present objective and subjective evidence of disease remission after induction and maintenance treatment with leukocyte apheresis. This is the first described case of successful maintenance treatment of severe Crohn's disease with leukocyte apheresis in the United Kingdom.

Provision of service and training for small bowel endoscopy in the UK.

OBJECTIVE: To determine the location and use of small bowel endoscopy services in the UK and to analyse training uptake to assess future demand and shape discussions about training and service delivery. DESIGN: Surveys of British Society of Gastroenterology (BSG) members by web-based and personal contact were conducted to ascertain capsule endoscopy practice and numbers of procedures performed. This was compared with expected numbers of procedures calculated using BSG guidelines, hospital episode statistics and published data of capsule endoscopy in routine practice. Analysis of data from two national training courses provided information about training. RESULTS: 45% of UK gastroenterology services offered in-house capsule endoscopy. 91.3% of survey responders referred patients for capsule endoscopy; 67.7% felt that local availability would increase referrals. Suspected small bowel bleeding and Crohn's disease were considered appropriate indications by the majority. Demand is increasing in spite of restricted use in 21.6% of centres. Only two regions performed more than the minimum estimate of need of 45 procedures per 250 000 population. Eight centres perform regular device-assisted enteroscopy; 14 services are in development. 74% of trainees were interested in training and of those training in image interpretation, 67% are doctors and 28% are nurses. CONCLUSIONS: Capsule endoscopy is used by the majority of UK gastroenterologists but appears to be underused. Current demand for device-assisted enteroscopy seems likely to be matched if new services become established. Future demand is likely to increase, however, suggesting the need to formalise training and accreditation for both doctors and nurses.

Optimizing quality of outpatient care for patients with inflammatory bowel disease: the importance of specialist clinics.

BACKGROUND: Most patients with inflammatory bowel disease (IBD) undergo long-term outpatient follow up. However, quality of care provided by specialist and non-specialist IBD clinics is rarely critically audited. OBJECTIVE: To compare the standard of outpatient care provided by general gastroenterology and specialist IBD clinics within a single hospital using defined quality criteria. METHODS: The case notes of 60 consecutive patients with IBD attending general gastroenterology clinics and of 100 patients attending the specialist IBD clinic were reviewed for fulfillment of six quality criteria over the preceding 18 months. RESULTS: The proportion of patients fulfilling all six criteria was higher in the specialist IBD clinic. In the specialist IBD clinic, compared with the general gastroenterology clinics, blood tests were performed with appropriate frequency during the initiation of immunosuppressive treatment in 7/11 versus 2/12 patients (P=0.04) and during maintenance in 24/31 versus 6/21 patients (P=0.001); bone protection with oral steroids were given to 25/53 versus 4/24 patients (P=0.01); a screening colonoscopy at 8-10 years was performed in 25/27 versus 11/20 patients with ulcerative colitis (P=0.004); annual serum urea and creatinine concentrations were measured in 82/89 versus 31/45 patients prescribed 5-aminosalicylates (P=0.001); annual liver function tests were performed in 96/100 versus 38/60 patients (P=0.001); and annual haematinics were measured in 37/47 versus 18/33 patients with Crohn's disease (P=0.03). CONCLUSION: By these criteria, the specialist IBD clinic provided better care than the non-specialist general gastroenterology clinics. Even in the specialist clinic, however, the care of a minority of patients did not fulfil certain criteria, emphasizing the need for a critical audit of outpatient management of IBD.

Interleukin-5 potentiates the growth response of Caco-2 cells to IGF-II: a role in colonic carcinogenesis complicating ulcerative colitis?

UNLABELLED: Longstanding ulcerative and Crohn's colitis increases the risk of colorectal cancer (CRC) compared to the general population. Elevated IGF-II mRNA and protein have been found in tumour tissue in sporadic CRC. The association of IGF-II in colitis-related-CRC is unknown. OBJECTIVES: To determine whether pro-inflammatory cytokines associated with colitis, namely IL-5, TNF-alpha and IL-1beta, alter the proliferative effect of IGF-II on the colorectal cancer cell line, Caco-2. DESIGN: Caco-2 cells were cultured with IGF-II and IL-5, TNF-alpha or IL-1beta. At 24 h intervals cell proliferation was assessed. The mechanism of action of any synergistic affect was investigated by RT-PCR to determine change in mRNA expression of IGF-II, IGF-1R or IGF-2R. RESULTS: After 72 h, IGF-II increased absorption (corresponding to cell density) compared to controls by 25% (p < 0.02). Co-incubation with IGF-II and IL-5 increased absorption by 42% (p < 0.001) compared to controls and 18% (p < 0.03) compared to IGF-II alone. Enhanced growth response was also seen with TNF-alpha and IL-1beta, but less so than IL-5. The IL-5 receptor was not expressed by Caco-2 cells and mRNA expression of the IGF-1R or IGF-2R was unchanged by incubation with cytokines. CONCLUSIONS: IGF-II promotes Caco-2 growth, an effect enhanced with IL-5, TNF-alpha and IL-1beta. The greatest response was with IL-5. This was IL-5 receptor-independent. Possible mechanisms include IL-5 interaction on an un-identified receptor or interference with IGF-binding proteins, as occurs with IL-1beta and IL-6. The enhanced growth response of Caco-2 cells to pro-inflammatory cytokines and IGF-II may have implications for the pathogenesis of CRC formation in colitis.

Gastrointestinal side effects of drugs.

Drugs can have adverse effects on any part of the gastrointestinal (GI) tract from mouth to colon. It is essential that a detailed and accurate drug history is taken in patients presenting with GI complaints. Many drug-induced effects will regress or heal on cessation of treatment. NSAIDs are usually associated with gastric and duodenal ulcers but are also recognised to cause lichen planus in the mouth, oesophageal inflammation and strictures, and small bowel and colonic ulcers and strictures. A newer class of anti-inflammatory drugs, the cyclooxygenase-2 (COX-2)-selective inhibitors, have been developed and have a more favourable GI safety profile than standard NSAIDs. Acute diarrhoea, relapse of inflammatory bowel disease (IBD), microscopic colitis and acute pancreatitis are also induced by ingestion of standard NSAIDs. The calcium antagonists, phenytoin and cyclosporin, induce gum hyperplasia, particularly in patients with poor oral hygiene. Alendronate, a bisphosphonate, has been associated with development of oesophageal ulcers, and specific recommendations are now given to reduce this complication. Of the many different forms of colitis associated with drug ingestion, the most frequent is pseudomembranous colitis. This is a complication of antibiotics and is caused by the toxin produced by Clostridium difficile. Many drugs have been associated with the development of acute pancreatitis, although a definite cause and effect relationship has been shown for only a few drugs. These include didanosine, furosomide, corticosteroids, azathioprine and sodium valproate.