Rationalizing polyp matching criteria in colon capsule endoscopy: an international expert consensus through RAND (modified DELPHI) process.

Background: Colon capsule endoscopy (CCE) has gained momentum as an alternative modality for the investigation of the lower gastrointestinal tract. Of the few challenges that remain, the comparison and - eventually - matching of polyps at different timestamps leads to the potential for double reporting and can contribute to false-positive findings and inaccuracies. With the impending artificial intelligence integration, the risk of double reporting the same polyp due to the lack of information on spatial orientation underscores the necessity for establishing criteria for polyp matching. Objectives: This RAND/University of California, Los Angeles (modified Delphi) process aims to identify the key factors or components used to match polyps within a CCE video. This involves exploring the attributes of each factor to create comprehensive polyp-matching criteria based on international expert consensus. Design: A systematic qualitative study using surveys. Methods: A panel of 11 international CCE experts convened to assess a survey comprised of 60 statements. Participants anonymously rated statement appropriateness on a 1-9 scale (1-3: inappropriate, 4-6: uncertain and 7-9: appropriate). Following a virtual group discussion of the Round 1 results, a Round 2 survey was developed and completed before the final analysis. Results: The factors that were agreed to be essential for polyp matching include (1) timestamp, (2) polyp localization, (3) polyp vascular pattern, (4) polyp size, (5) time interval of the polyp appearance between the green and yellow camera, (6) surrounding tissue, (7) polyp morphology and (8) polyp surface and contour. When five or more factors are satisfied, it was agreed that the comparing polyps are likely the same polyp. Conclusion: This study has established the first complete criteria for polyp matching in CCE. While it might not provide a definitive solution for matching difficult, small and common polyps, these criteria serve as a framework to guide and facilitate the process of polyp-matching.

Creating criteria and standards for matching polyps (abnormal growth in the bowels) on colon capsule video analysis: an international expert agreement using the RAND (modified Delphi process) process Background: Doctors often use colon capsule endoscopy (CCE), a high-tech capsule with two cameras, to record and check for diseases in the small and large bowels as the capsule travels through the intestines. One of the most common conditions in the large bowel is polyps, which are abnormal growths in the lining of the bowel. Comparing and matching polyps in the same video from the capsule can be tricky as they look very similar, leading to the possibility of incorrectly reporting the same polyp twice or more. This can lead to wrong results and inaccuracies. The literature did not have any criteria or standards for matching polyps in CCE before. Aim: Using the RAND/UCLA (modified Delphi) process, this study aims to identify the key factors or components used to match polyps within a CCE video. The goal is to explore each factor and create complete criteria for polyp matching based on the agreement from international experts. Method: A group of 11 international CCE experts came together to evaluate a survey with 60 statements. They anonymously rated each statement on a scale from 1 to 9 (1-3: inappropriate, 4-6: uncertain, and 7-9: appropriate). After discussing the Round 1 results virtually, a Round 2 survey with the same but revised questions was created and completed before the final analysis of their agreement. Results: The main factors for matching polyps are 1) the timing when the polyp was seen, 2) where it is in the bowel, 3) its blood vessel pattern, 4) size, 5) the timing of its appearance between cameras, 6) surrounding tissue features, 7) its shape, and 8) surface features. If five or more of these factors match, the compared polyps are likely the same. Conclusion: This study establishes the first complete criteria for matching polyps in CCE. While it may not provide a definitive solution for matching challenging and small polyps, these criteria serve as a guide to help and make the process of polyp matching easier.

Factors influencing gastrostomy tube removal.

BACKGROUND: When commencing enteral feeding, patients and families will want to know the likelihood of returning to an oral diet. There is a paucity of data on the prognosis of patients with gastrostomies. We describe a large dataset of patients, which identifies factors influencing gastrostomy removal and assesses the likelihood of the patient having at home enteral nutrition. METHODS: Retrospective data was collected on patients from Sheffield Teaching Hospitals who had received a gastrostomy and had outpatient enteral feeding between January 2016 and December 2019. Demographic data, indication and outcomes were analysed. RESULTS: A total of 451 patients were assessed, median age: 67.7. 183/451(40.6%) gastrostomies were for head and neck cancer, 88/451 (19.5%) for stroke, 28/451 (6.2%) for Motor Neuron Disease, 32/451 (7.1%) for other neurodegenerative causes, 120/451 (26.6%) other. Of the 31.2% who had their gastrostomy removed within 3 years, head and neck cancer was the most common indication (58.3%) followed by stroke (10.2%), Motor Neuron Disease (7.1%) and other neurodegenerative diseases (3.1%). Gastrostomy removal was significantly influenced by age, place of residence, and having head and neck cancer (p < 0.05). There was the greatest likelihood of removal within the first year (24%). 70.5% had enteral feeding at home. CONCLUSION: This large cohort study demonstrates 31.2% of patients had their gastrostomy removed within 3 years. Head and neck cancer patients, younger age and residing at home can help positively predict removal. Most patients manage their feeding at home rather than a nursing home. This study provides new information on gastrostomy outcomes when counselling patients to provide realistic expectations.

What is the role of out of programme clinical fellowships in the era of Shape of Training? A single-centre cohort study.

BACKGROUND: The updated Shape of Training curriculum has shortened the duration of specialty training. We present the potential role of out of programme clinical fellowships. METHOD: An electronic online survey was sent to all current fellows to understand their experiences, training opportunities and motivations.Data were collected on fellows' endoscopic experiences and publications using PubMed for all previous doctors who have completed the Sheffield Fellowship Programme. RESULTS: Since 2004, 39 doctors have completed the Sheffield Fellowship.Endoscopic experience: current fellows completed a median average of 350 (IQR 150-500) gastroscopies and 150 (IQR 106-251) colonoscopies per year. Fellows with special interests completed either 428 hepato-pancreato-biliary procedures or 70 endoscopic mucosal resections per year.Medline publications: Median average 9 publications(IQR 4-17). They have also received multiple national or international awards and 91% achieved a doctoral degree.The seven current fellows in the new Shape of Training era (57% male, 29% Caucasian, aged 31-40 years) report high levels of enjoyment due to their research projects, supervisory teams and social aspects. The most cited reasons for undertaking the fellowship were to develop a subspecialty interest, take time off the on-call rota and develop endoscopic skills. The most reported drawback was a reduced income.All current fellows feel that the fellowship has enhanced their clinical confidence and prepared them to become consultants. CONCLUSION: Out of programme clinical fellowships offer the opportunity to develop the required training competencies, subspecialty expertise and research skills in a supportive environment.

Idiopathic terminal ileitis: myth or true entity?

PURPOSE OF REVIEW: Isolated terminal ileitis is an increasing phenomenon identified during colonoscopy. Idiopathic terminal ileitis (IDTI) is a diagnosis of exclusion, representing a significant challenge from a diagnostic and management point of view. This review provides an overview of the most recent and relevant evidence on idiopathic IDTI, focusing on its evolution, the natural history and the management strategies proposed in the literature. RECENT FINDINGS: IDTI is uncommon, with a reported prevalence between 0.5 and 7%. The main differential is with Crohn's disease and intestinal tuberculosis in endemic countries. A proportion of patients (0-50%) can progress and develop Crohn's disease; however, there are no reliable predictive factors to stratify IDTI patients. SUMMARY: IDTI is a challenging entity, with a small proportion of patients progressing to Crohn's disease over time thus requiring follow-up. Noninvasive modalities such as capsule endoscopy are useful for follow-up, but further research is required to better understand this entity.

Endoscopic Ruler for varix size measurement: A multicenter pilot study.

BACKGROUND: We invented Endoscopic Ruler, a new endoscopic device to measure the size of varices in patients with cirrhosis and portal hypertension. AIM: To assess the feasibility and safety of Endoscopic Ruler, and evaluate the agreement on identifying large oesophageal varices (OV) between Endoscopic Ruler and the endoscopists, as well as the interobserver agreement on diagnosing large OV using Endoscopic Ruler. METHODS: We prospectively and consecutively enrolled patients with cirrhosis from 11 hospitals, all of whom got esophagogastroduodenoscopy (EGD) with Endoscopic Ruler. The primary study outcome was a successful measurement of the size of varices using Endoscopic Ruler. The secondary outcomes included adverse events, operation time, the agreement of identifying large OV between the objective measurement of Endoscopic Ruler and the empirical reading of endoscopists, together with the interobserver agreement on diagnosing large OV by Endoscopic Ruler. RESULTS: From November 2020 to April 2022, a total of 120 eligible patients with cirrhosis were recruited and all of them underwent EGD examinations with Endoscopic Ruler successfully without any adverse event. The median operation time of Endoscopic Ruler was 3.00 min [interquartile range (IQR): 3.00 min]. The kappa value between Endoscopic Ruler and the endoscopists while detecting large OV was 0.52, demonstrating a moderate agreement. The kappa value for diagnosing large OV using Endoscopic Ruler among the six independent observers was 0.77, demonstrating a substantial agreement. CONCLUSION: The data demonstrates that Endoscopic Ruler is feasible and safe for measuring the size of varices in patients with cirrhosis and portal hypertension. Endoscopic Ruler is potential to promote the clinical practice of the two-grade classification system of OV.

Cost comparison of oral, transnasal and magnet assisted capsule endoscopy in the examination of the upper gastrointestinal tract in patients with dyspepsia.

Introduction: Conventional oral upper gastrointestinal (GI) endoscopy can obe uncomfortable. By comparison, transnasal endoscopy (TNE) and magnet assisted capsule endoscopy (MACE) have superior tolerability. A cost comparison of competing upper GI endoscopic modalities have yet to be performed. Methods: We performed a cost comparison study of oral, TNE and MACE by a combination of activity-based costing and averaging of fixed costs over 24 481 upper GI endoscopies performed for dyspepsia over a 10-year period. Results: On average, 9.4 procedures were performed daily. TNE was cheapest at €125.90 per procedure, costing 30% less than oral endoscopy at €184.10 and threefold cheaper than MACE at €407.10. Flexible endoscope reprocessing cost €53.80. TNE was cheaper than oral endoscopy as sedation was not required. Oral endoscopies have a further rate of infectious complications, estimated to cost €16.20 per oral procedure in inpatient admissions. Oral and TNE equipment are more expensive to purchase and maintain than MACE costing €79 330 and €81 819, respectively compared with MACE at €15 420 per annum. However, capsule endoscopes cost significantly more per procedure at €369.00 than the consumables for flexible endoscopy (per oral €12.30, TNE €5.30). Conclusions: TNE cost less to perform than conventional per oral endoscopy. The cost of capsule endoscopes will need to be reduced significantly if routine use is to be expected.

A retrospective study of outcomes and the validation of the Sheffield Gastrostomy Score in PEGs, RIGs and PIGs.

INTRODUCTION: There are limited studies comparing the safety and effectiveness of Radiologically Assisted Gastrostomies (RAGs) against Percutaneous Endoscopic Gastrostomies (PEGs). The Sheffield Gastrostomy Score (SGS) can be used to help predict 30-day mortality, more information is needed on its validity in RAGs. Our aim is to compare mortality between RAGs (Radiologically Inserted Gastrostomies (RIGs) and Per-oral Image Guided Gastrostomies (PIGs)) with PEGs and validate the SGS. METHOD: Data on gastrostomies newly inserted in three hospitals from 2016-2019 were retrospectively collected. Demographics, indication, insertion date, date of death, inpatient status and blood tests (albumin, CRP and eGFR) were recorded. RESULTS: 1977 gastrostomies were performed: Gastrostomy mortality at 7 days was 1.3% and at 30 days was 6%. There was a 5% 30-day mortality for PEGs, 5.5% RIGs, 7.2% PIGs (p = 0.215). Factors increasing 30 day mortality were age ≥60 years (p = 0.039), albumin <35 g/L (p = 0.005), albumin <25 g/L (p < 0.001) and CRP ≥10 mg/L (p < 0.001). For patients who died within 30 days; 0.6% had an SGS of 0, 3.7% = 1, 10.2% = 2 and 25.5% = 3, with similar trends for RAGs and PEGs. ROC curves showed the area under the curve for all gastrostomies, RAGs and PEGs as 0.743, 0.738, 0.787 respectively. DISCUSSION: There was no significant difference between 30-day mortality for PEGs, RIGs and PIGs. Factors predicting risk include age ≥60 years, albumin <35 g/L, albumin <25 g/L and CRP ≥10 mg/L. The SGS has been validated in this study for PEGs and for the first time in RAGs as well..

Colon Capsule Endoscopy - Shining the Light through the Colon.

PURPOSE OF REVIEW: Colon capsule endoscopy (CCE) is a non-invasive, wireless capsule endoscope. In this article, we review its current applications, compare its performance with optical colonoscopy (OC) and alternative imaging modalities like CT colonography (CTC), and highlight developments that may increase potential future use. RECENT FINDINGS: By comparison to OC both CCE and CTC have a good sensitivity and specificity in detecting colonic polyps. CCE is more sensitive in detecting sub centimetre polyps. CCE is capable of detecting colonic inflammation and anorectal pathologies, commonly missed by CTC. However, rates of complete CCE examinations are limited by inadequate bowel preparation or incomplete colonic transit, whereas CTC can be performed with less bowel purgatives. Patients tolerate CCE better than OC, however patient preference between CCE and CTC vary. CCE and CTC are both reasonable alternatives to OC. Strategies to improve completion rates and adequacy of bowel preparation will improve cost and clinical effectiveness of CCE.

What is the current provision of service for gastrostomy insertion in England?

Background: Significant morbidity and mortality can be associated with gastrostomy insertion, likely influenced by patient selection, indication and aftercare. We aimed to establish what current variation in practice exists and how this has improved by comparison to our previously published British Society of Gastroenterology survey of 2010. Methods: We approached all National Health Service (NHS) hospitals in England (n=198). Email and web-based questionnaires were circulated. These data were correlated with the National Endoscopy Database (NED). Results: The response rate was 69% (n=136/198). Estimated Percutaneous Endoscopic Gastrostomy (PEG) placements in the UK are currently 6500 vs 17 000 in 2010 (p<0.01). There is a dedicated PEG consultant involved in 59% of the centres versus 30% in 2010 (p<0.001). Multidisciplinary team meeting (MDT) discussion occurs in 66% versus 40% in 2010 (p<0.05). Formal aftercare provision occurs in 83% versus 64% in 2010 (p<0.001). 74/107 respondents (69%) reported feeling pressurised to authorise a gastrostomy. Conclusion: This national survey, validated by the results from NED, demonstrates a reduction of over 60% for PEG insertion rates compared with previous estimates. There has also been an increase in consultant involvement, MDT discussion and aftercare provision. However, two-third of responders described 'pressure' to insert a gastrostomy. Perhaps further efforts are needed to include and educate other specialty teams, patients and next of kin.

Quantification of Celiac Disease Severity Using Video Capsule Endoscopy: A Comparison of Human Experts and Machine Learning Algorithms.

BACKGROUND: Video capsule endoscopy (VCE) is an attractive method for diagnosing and objectively monitoring disease activity in celiac disease (CeD). Its use, facilitated by artificial intelligence- based tools, may allow computer-assisted interpretation of VCE studies, transforming a subjective test into a quantitative and reproducible measurement tool. OBJECTIVE: To evaluate and compare objective CeD severity assessment as determined with VCE by expert human readers and a machine learning algorithm (MLA). METHODS: Patients ≥ 18 years with histologically proven CeD underwent VCE. Examination frames were scored by three readers from one center and the MLA, using a 4-point ordinal scale for assessing the severity of CeD enteropathy. After scoring, curves representing CeD severity across the entire small intestine (SI) and individual tertiles (proximal, mid, and distal) were fitted for each reader and the MLA. All comparisons used Krippendorff's alpha; values > 0.8 represent excellent to 'almost perfect' inter-reader agreement. RESULTS: VCEs from 63 patients were scored. Readers demonstrated strong inter-reader agreement on celiac villous damage (alpha=0.924), and mean value reader curves showed similarly excellent agreement with MLA curves (alpha=0.935). Average reader and MLA curves were comparable for mean and maximum values for the first SI tertile (alphas=0.932 and 0.867, respectively) and the mean value over the entire SI (alpha=0.945). CONCLUSION: A novel MLA demonstrated excellent agreement on whole SI imaging with three expert gastroenterologists. An ordinal scale permitted high inter-reader agreement, accurately and reliably replicated by the MLA. Interpreting VCEs using MLAs may allow automated diagnosis and disease burden assessment in CeD.

Does reverse mentoring work in the NHS: a feasibility study of clinicians in practice.

OBJECTIVE: To assess the risks and benefits of reverse mentoring of consultants by junior doctors. DESIGN: A feasibility study divided into two phases: first a semistructured interview where performance of participating consultants was assessed by junior doctors and then a second phase allowing for feedback to be given on a one-to-one basis. Data collected through questionnaires with free text questions and Likert scores. SETTING: Tertiary teaching hospital in the UK. PARTICIPANTS: Six junior doctors (66.6% male, age range 31-40 years) and five consultants (80% male, age range 35-65 years and consultants for 5-20 years). INTERVENTION: Reverse mentoring session. MAIN OUTCOME MEASURE: The concerns and/or benefits of the process of reverse mentoring. Confidence was assessed in 7 domains: clinical practice, approach to juniors, approachability, use of technology, time management, strengths and areas for improvement using Likert scales giving a total out of 35. RESULTS: The most common concerns cited were overcoming the hierarchical difference and a selection bias in both mentors and mentees. However, no participant experienced this hierarchical difference through the reverse mentoring process and no relationships were negatively affected. Mentors became more confident in feeding back to seniors (23 vs 29 out of 35, p=0.04) most evident in clinical practice and areas to improve (3 vs 4 out of 5, p=0.041 and 3 vs 5 out of 5, p=0.041, respectively). CONCLUSION: We present the first study of reverse mentoring in an NHS clinical setting. Initial concerns with regard to damaged relationships and hierarchical gradients were not experienced and all participants perceived that they benefited from the process. Reverse mentoring can play a role in engaging and training future leaders at junior stages and provide a means for consultants to receive valuable feedback from junior colleagues.

Score reproducibility and reliability in differentiating small bowel subepithelial masses from innocent bulges.

AIMS: The primary aim of this study was to assess the reliability, intra- and inter-observer variation of the SPICE, Mucosal protrusion angle (MPA) and SHYUNG scores in differentiating a subepithelial mass (SEM) from a bulge. METHODS: This retrospective multicentre study analysed the 3 scores, radiological studies, enteroscopy and/or surgical findings. RESULTS: 100 patients with a potential SEM (mean age 57.6years) were recruited with 75 patients having pathology. In patients with a SEM the mean SPICE score was 2.04 (95% CI 1.82-2.26) as compared to 1.16 (95% CI 0.81-1.51) without any pathology (AUC 0.74, p<0.001), with a fair intra-observer agreement (Kappa 0.3, p<0.001) and slight inter-observer agreement (Kappa 0.14, p<0.05). SPICE had a 37.3% sensitivity and 92.0% specificity in distinguishing between a SEM and bulge, whereas MPA<90˚ had 58.7% and 76.0% respectively, with poor intra-observer(p = 0.05) and interobserver agreement (p = 0.64). The SHYUNG demonstrated a moderate intra-observer (Kappa 0.44, p<0.001) and slight inter-observer reliability (Kappa 0.18, p<0.001). The sensitivity of an elevated SHYUNG score (≥4) in identifying a SEM was 18.7% with a specificity of 92.0% (AUC 0.71, p = 0.002). CONCLUSIONS: Though these scores are easy to use, they have, at best, slight to moderate intra and inter-observer agreement. Their overall diagnostic performances are limited.

Comparison of patient tolerance and acceptability of magnet-controlled capsule endoscopy and flexible endoscopy in the investigation of dyspepsia.

Background and study aims Oropharyngeal intubation during Esophagogastroduodenoscopy (EGD) is uncomfortable, associated with aerosol generation and transmission of airborne microbes. Less-invasive alternatives may be better tolerated. In this study, patient tolerance and acceptability of EGD and transnasal endoscopy (TNE) have been compared with magnet-controlled capsule endoscopy (MACE). Patients and methods A comparison of MACE with EGD and TNE in the investigation of dyspepsia was performed. Factors affecting patient tolerance and acceptability were examined using the Endoscopy Concerns Scale (ECS) and Universal Patient Centeredness Questionnaire (UPC-Q). Results Patients were significantly more distressed (scoring least to most distress: 1-10) by gagging (6 vs 1), choking (5 vs 1), bloating (2 vs 1), instrumentation (4 vs 1), discomfort during (5 vs 1) and after (2 vs 1) EGD compared to MACE (all P  < 0.0001). Patients were more distressed by instrumentation (5 vs 1) and discomfort during (5 vs 1) TNE compared to MACE ( P  = 0.001). Patients were more accepting of MACE than EGD and TNE with a UPC-Q score (scoring least to most acceptable: 0-100) lower for EGD (50 vs 98, P  < 0.0001) and TNE (75 vs 88, P  = 0.007) than MACE, and a post-procedure ECS score (scoring most to least acceptable: 10-100) higher for EGD (34 vs 11, P  < 0.0001) and TNE (25 vs 10.5, P  = 0.001) than MACE. MACE would be preferred by 83 % and 64 % of patients even if EGD or TNE respectively was subsequently recommended to obtain biopsies in half of examinations. Conclusions Gagging and choking during instrumentation, the main causes of patient distress during EGD, occurred less during TNE but tolerance, acceptability and patient experience favored MACE.

Capsule endoscopy - a non-invasive modality to investigate the GI tract: out with the old and in with the new?

INTRODUCTION: Capsule endoscopy has had significant development since it was introduced into the field of medicine in 2000. It is non-invasive, well tolerated, does not require sedation and is a first-line small bowel investigative modality. As it transits through the entire gastrointestinal (GI) tract, it has the potential to provide a pan-enteric examination. AREAS COVERED: In this review we will discuss the new diagnostic modalities along with traditional methods which have been used for examination of the gastro intestinal (GI) tract. The main focus of this review will be on the use of capsule endoscopy for pan-enteric examination. EXPERT OPINION: Capsule endoscopy is an accepted first-line investigation for the small bowel. Diagnostic sensitivity of the colon capsule is comparable to colonoscopy in controlled trials and is being evaluated in high-risk patients in routine clinical practice in national programs. Preliminary data suggest that a magnetic-controlled examination of the upper GI tract could be developed to enable a complete upper GI examination.

Training pathway for small bowel capsule endoscopy in the UK.

The demand for small bowel (SB) capsule endoscopy (CE) is increasing in the UK. However, there remains a wide variation in the number of CE procedures performed in different centres. Across the UK there is a lack of a clear training pathway or certification process. A standardised national Joint Advisory Group (JAG) on Gastrointestinal Endoscopy approved a 1-year training and accreditation programme accessible to all professional groups that may wish to train in SB CE. Structured training is delivered using JAG-accredited CE courses and an electronic learning module. Prior to setting a knowledge-based assessment, a minimum of 50 SB CE cases are recommended to be read in tandem with a trainer at a local centre, with proficiency documented using Direct Observation of Procedural Skill (DOPS) assessments.

Cryptogenic multifocal ulcerating stenosing enteritis and other under-recognised small bowel inflammatory enteropathies.

PURPOSE OF REVIEW: Capsule endoscopy and more sensitive radiological techniques have resulted in more enteropathies being detected. A rare disease of unknown aetiology, 'cryptogenic multifocal ulcerating stenosing enteritis' or 'chronic nonspecific multiple ulcers of the small intestine' (CNSU), has long been recognised. This review aims to describe how disease can be better diagnosed and differentiated from other small bowel inflammatory disorders. RECENT FINDINGS: Genetic studies have shown that some patients with CNSU (the term used in Japanese studies) express SLCO2A1 gene mutations, a gene which encodes a prostaglandin transporter expressed on vascular endothelium, allowing a more specific diagnosis of 'chronic enteropathy associated with SLCO2A1'. Mutations in the PLA2G4A gene result in cytosolic phospholipase A2α deficiency and reduced arachidonic acid for prostaglandin synthesis leading to a severe ulcerating, stenosing and fistulating small bowel disease. SUMMARY: A 'prostaglandin-related enteropathy' should be considered in patients with atypical small bowel ulceration and stenosis. Genetic analysis will allow the detection of SLCO2A1 and PLA2G4A gene mutations. However, a careful history of medication use and a urinary metabolite screen may reveal the use of nonsteroidal anti-inflammatory drugs, a common cause of small bowel injury which is well recognised as being mediated by prostaglandin inhibition.

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.