Application of small bowel capsule endoscopy in children with Meckel's diverticulum.

BACKGROUND: Meckel diverticulum (MD) is an important cause of gastrointestinal bleeding in children. Small bowel capsule endoscopy (SBCE) is a first-line examination method applied to patients with obscure gastrointestinal bleeding, but there are few studies on its application in children with MD. This article aims to provide evidence in favor of the auxiliary diagnosis of MD in children by analyzing its characteristics using SBCE. METHODS: We retrospectively collected the clinical data of patients with suspected MD. RESULTS: A total of 58 children were included in this study. All 58 children presented overt gastrointestinal bleeding (bloody stool or melena). Capsule endoscopy identified protruding lesions in 2 cases, double-lumen changes in 30 cases (all considered as MD), vascular lesions in 7 cases, intestinal mucosal inflammatory lesions in 3 cases, ulcers or erosion in 3 cases, and no obvious abnormalities in SBCE in 12 cases. Both SBCE and technetium-99 scans were performed for 24 cases, 22 of which were diagnosed MD by their combined results, giving a diagnostic coincidence rate of 91.7%. Eight cases were highly suspected as MD but were negative for the technetium-99 scan and positive for SBCE. CONCLUSION: SBCE has high accuracy in the diagnosis of MD in children, especially when performed in combination with a technetium-99 scan, which can greatly improve the diagnostic rate of MD in children.

Efficacy and safety of three-dimensional magnetically assisted capsule endoscopy for upper gastrointestinal and small bowel examination.

BACKGROUND: Magnetically assisted capsule endoscopy (MACE) showed the feasibility for upper gastrointestinal examination. To further enhance the performance of conventional MACE, it is necessary to provide quality-improved and three-dimensional images. The aim of this clinical study was to determine the efficacy and safety of novel three-dimensional MACE (3D MACE) for upper gastrointestinal and small bowel examination at once. METHODS: This was a prospective, single-center, non-randomized, and sequential examination study (KCT0007114) at Dongguk University Ilsan Hospital. Adult patients who visited for upper endoscopy were included. The study protocol was conducted in two stages. First, upper gastrointestinal examination was performed using 3D MACE, and a continuous small bowel examination was performed by conventional method of capsule endoscopy. Two hours later, an upper endoscopy was performed for comparison with 3D MACE examination. The primary outcome was confirmation of major gastric structures (esophagogastric junction, cardia/fundus, body, angle, antrum, and pylorus). Secondary outcomes were confirmation of esophagus and duodenal bulb, accuracy for gastric lesions, completion of small bowel examination, 3D image reconstruction of gastric lesion, and safety. RESULTS: Fifty-five patients were finally enrolled. The examination time of 3D MACE was 14.84 ± 3.02 minutes and upper endoscopy was 5.22 ± 2.39 minutes. The confirmation rate of the six major gastric structures was 98.6% in 3D MACE and 100% in upper endoscopy. Gastric lesions were identified in 43 patients during 3D MACE, and 40 patients during upper endoscopy (Sensitivity 0.97). 3D reconstructed images were acquired for all lesions inspected by 3D MACE. The continuous small bowel examination by 3D MACE was completed in 94.5%. 3D MACE showed better overall satisfaction (3D MACE 9.55 ± 0.79 and upper endoscopy 7.75 ± 2.34, p<0.0001). There were no aspiration or significant adverse event or capsule retention in the 3D MACE examination. CONCLUSIONS: Novel 3D MACE system is more advanced diagnostic modality than the conventional MACE. And it is possible to perform serial upper gastrointestinal and small bowel examination as a non-invasive and one-step test. It would be also served as a bridge to pan-endoscopy.

Artificial intelligence in detection of small bowel lesions and their bleeding risk: A new step forward.

The present letter to the editor is related to the study with the title "Automatic detection of small bowel (SB) lesions with different bleeding risk based on deep learning models". Capsule endoscopy (CE) is the main tool to assess SB diseases but it is a time-consuming procedure with a significant error rate. The development of artificial intelligence (AI) in CE could simplify physicians' tasks. The novel deep learning model by Zhang et al seems to be able to identify various SB lesions and their bleeding risk, and it could pave the way to next perspective studies to better enhance the diagnostic support of AI in the detection of different types of SB lesions in clinical practice.

Terminal ileitis: a rare gastrointestinal manifestation of IgA vasculitis in a child.

A girl in middle childhood was referred to the paediatric surgical team with acute colicky abdominal pain and bile-stained vomiting. This was preceded by a viral illness. Investigations revealed raised inflammatory markers, and imaging of the abdomen demonstrated ileal and jejunal thickening. Concerns were raised regarding whether she had inflammatory bowel disease. Endoscopy revealed gastritis and duodenitis, and colonoscopy was unremarkable. Video capsule endoscopy demonstrated ulcers in the jejunum and ileum.On day 8 of admission, she developed a symmetrical purpuric rash over both ankles leading to the diagnosis of Henoch-Schonlein-related ileitis. Multidisciplinary team working led to appropriate management of the patient and avoided surgery. Video capsule endoscopy enabled visualisation of the small bowel. She was managed with 5 days of methylprednisolone followed by oral steroids. She made a good recovery with no sequelae. This case highlighted that terminal ileitis is a rare complication of IgA vasculitis with a good prognosis.

Robotic wireless capsule endoscopy: recent advances and upcoming technologies.

Wireless capsule endoscopy (WCE) offers a non-invasive evaluation of the digestive system, eliminating the need for sedation and the risks associated with conventional endoscopic procedures. Its significance lies in diagnosing gastrointestinal tissue irregularities, especially in the small intestine. However, existing commercial WCE devices face limitations, such as the absence of autonomous lesion detection and treatment capabilities. Recent advancements in micro-electromechanical fabrication and computational methods have led to extensive research in sophisticated technology integration into commercial capsule endoscopes, intending to supersede wired endoscopes. This Review discusses the future requirements for intelligent capsule robots, providing a comparative evaluation of various methods' merits and disadvantages, and highlighting recent developments in six technologies relevant to WCE. These include near-field wireless power transmission, magnetic field active drive, ultra-wideband/intrabody communication, hybrid localization, AI-based autonomous lesion detection, and magnetic-controlled diagnosis and treatment. Moreover, we explore the feasibility for future "capsule surgeons".

Detachable string magnetically controlled capsule endoscopy for the noninvasive diagnosis of esophageal diseases: A prospective, blind clinical study.

BACKGROUND: Traditional esophagogastroduodenoscopy (EGD), an invasive examination method, can cause discomfort and pain in patients. In contrast, magnetically controlled capsule endoscopy (MCE), a noninvasive method, is being applied for the detection of stomach and small intestinal diseases, but its application in treating esophageal diseases is not widespread. AIM: To evaluate the safety and efficacy of detachable string MCE (ds-MCE) for the diagnosis of esophageal diseases. METHODS: Fifty patients who had been diagnosed with esophageal diseases were prospectively recruited for this clinical study and underwent ds-MCE and conventional EGD. The primary endpoints included the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of ds-MCE for patients with esophageal diseases. The secondary endpoints consisted of visualizing the esophageal and dentate lines, as well as the subjects' tolerance of the procedure. RESULTS: Using EGD as the gold standard, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of ds-MCE for esophageal disease detection were 85.71%, 86.21%, 81.82%, 89.29%, and 86%, respectively. ds-MCE was more comfortable and convenient than EGD was, with 80% of patients feeling that ds-MCE examination was very comfortable or comfortable and 50% of patients believing that detachable string v examination was very convenient. CONCLUSION: This study revealed that ds-MCE has the same diagnostic effects as traditional EGD for esophageal diseases and is more comfortable and convenient than EGD, providing a novel noninvasive method for treating esophageal diseases.

AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study.

BACKGROUND: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. METHODS: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. FINDINGS: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p<0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6-19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p<0·0001). INTERPRETATION: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. FUNDING: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.

Automated detection of small bowel lesions based on capsule endoscopy using deep learning algorithm.

BACKGROUND: In order to overcome the challenges of lesion detection in capsule endoscopy (CE), we improved the YOLOv5-based deep learning algorithm and established the CE-YOLOv5 algorithm to identify small bowel lesions captured by CE. METHODS: A total of 124,678 typical abnormal images from 1,452 patients were enrolled to train the CE-YOLOv5 model. Then 298 patients with suspected small bowel lesions detected by CE were prospectively enrolled in the testing phase of the study. Small bowel images and videos from the above 298 patients were interpreted by the experts, non-experts and CE-YOLOv5, respectively. RESULTS: The sensitivity of CE-YOLOv5 in diagnosing vascular lesions, ulcerated/erosive lesions, protruding lesions, parasite, diverticulum, active bleeding and villous lesions based on CE videos was 91.9 %, 92.2 %, 91.4 %, 93.1 %, 93.3 %, 95.1 %, and 100 % respectively. Furthermore, CE-YOLOv5 achieved specificity and accuracy of more than 90 % for all lesions. Compared with experts, the CE-YOLOv5 showed comparable overall sensitivity, specificity and accuracy (all P > 0.05). Compared with non-experts, the CE-YOLOv5 showed significantly higher overall sensitivity (P < 0.0001) and overall accuracy (P < 0.0001), and a moderately higher overall specificity (P = 0.0351). Furthermore, the time for AI-reading (5.62 ± 2.81 min) was significantly shorter than that for the other two groups (both P < 0.0001). CONCLUSIONS: CE-YOLOv5 diagnosed small bowel lesions in CE videos with high sensitivity, specificity and accuracy, providing a reliable approach for automated lesion detection in real-world clinical practice.

An ingestible near-infrared fluorescence capsule endoscopy for specific gastrointestinal diagnoses.

Early diagnosis of gastrointestinal (GI) diseases is important to effectively prevent carcinogenesis. Capsule endoscopy (CE) can address the pain caused by wired endoscopy in GI diagnosis. However, existing CE approaches have difficulty effectively diagnosing lesions that do not exhibit obvious morphological changes. In addition, the current CE cannot achieve wireless energy supply and attitude control at the same time. Here, we successfully developed a novel near-infrared fluorescence capsule endoscopy (NIFCE) that can stimulate and capture near-infrared (NIR) fluorescence images to specifically identify subtle mucosal microlesions and submucosal lesions while capturing conventional white light (WL) images to detect lesions with significant morphological changes. Furthermore, we constructed the first synergetic system that simultaneously enables multi-attitude control in NIFCE and supplies long-term power, thus addressing the issue of excessive power consumption caused by the NIFCE emitting near-infrared light (NIRL). We performed in vivo experiments to verify that the NIFCE can specifically "light up" tumors while sparing normal tissues by synergizing with probes actively aggregated in tumors, thus realizing specific detection and penetration. The prototype NIFCE system represents a significant step forward in the field of CE and shows great potential in efficiently achieving early targeted diagnosis of various GI diseases.

Capsule endoscopy and panendoscopy: A journey to the future of gastrointestinal endoscopy.

In 2000, the small bowel capsule revolutionized the management of patients with small bowel disorders. Currently, the technological development achieved by the new models of double-headed endoscopic capsules, as miniaturized devices to evaluate the small bowel and colon [pan-intestinal capsule endoscopy (PCE)], makes this non-invasive procedure a disruptive concept for the management of patients with digestive disorders. This technology is expected to identify which patients will require conventional invasive endoscopic procedures (colonoscopy or balloon-assisted enteroscopy), based on the lesions detected by the capsule, i.e., those with an indication for biopsies or endoscopic treatment. The use of PCE in patients with inflammatory bowel diseases, namely Crohn's disease, as well as in patients with iron deficiency anaemia and/or overt gastrointestinal (GI) bleeding, after a non-diagnostic upper endoscopy (esophagogastroduodenoscopy), enables an effective, safe and comfortable way to identify patients with relevant lesions, who should undergo subsequent invasive endoscopic procedures. The recent development of magnetically controlled capsule endoscopy to evaluate the upper GI tract, is a further step towards the possibility of an entirely non-invasive assessment of all the segments of the digestive tract, from mouth-to-anus, meeting the expectations of the early developers of capsule endoscopy.

Capsules for the Diagnosis and Treatment of Gastrointestinal Motility Disorders- A Game Changer.

PURPOSE OF REVIEW: Over the last few decades, there have been remarkable strides in endoscopy and radiological imaging that have advanced gastroenterology. However, the management of neurogastroenterological disorders has lagged behind, in part handicapped by the use of catheter-based manometry that is both non-physiological and uncomfortable. The advent of capsule technology has been a game changer for both diagnostic and therapeutic applications. RECENT FINDINGS: Here, we discuss several capsule devices that are available or under investigation. There are three technologies that are FDA approved. Wireless motility capsule measures pH and pressure and provides clinically impactful information regarding gastric, small intestine and colonic transit, without radiation that has been demonstrated to guide management of gastroparesis, dyspepsia and constipation. Wireless ambulatory pH monitoring capsule is currently the gold standard for assessing gastroesophageal acid reflux. In the therapeutics arena, an orally ingested vibrating capsule has been recently FDA approved for the treatment of chronic constipation, supported by a robust phase 3 clinical trial which showed significant improvement in constipation symptoms and quality of life. There are several capsules currently under investigation. Smart capsule bacterial detection system and Capscan® are capsules that can sample fluid in the small or large bowel and provide microbiome analysis for detection of small intestinal bacterial (SIBO) or fungal overgrowth (SIFO). Another investigational gas sensing capsule analyzing hydrogen, CO2, volatile fatty acids and capsule orientation, can measure regional gut transit time and luminal gas concentrations and assess gastroparesis, constipation or SIBO. Therapeutically, other vibrating capsules are in development. Innovations in capsule technology are poised to transform our ability to investigate gut function physiologically, and non-invasively deliver targeted treatment(s), thereby providing both accurate diagnostic information and luminally-directed, safe therapy.

Emergent approach to small bowel tumors: diagnosis and treatment.

BACKGROUND: This study presents the diagnosis and treatment of rare small bowel tumors through clinical cases. METHODS: Patients treated between 2000 and 2023 were included in the study. The clinical records of the patients were analyzed retrospectively. RESULTS: A total of 34 patients were included in the study. Of these patients, 26 (75.5%) were male and eight (23.5%) were female. The mean age of the patients was 62.1 years. The most common symptoms and signs were abdominal pain (76.4%), bloating (38.2%), and nausea and vomiting (17.6%). Diagnostic methods included computed tomography (CT) (82.3%), upper gastrointestinal double balloon enteroscopy (35.2%), and capsule endoscopy (5.8%). Diagnoses included adenocarcinoma in 13 cases, gastrointestinal stromal tumors (GISTs) in 12 cases, and neuroendocrine tumors (NETs) in two cases. CONCLUSION: Small bowel tumors frequently present with abdominal pain, bloating, and nausea and vomiting. CT and endoscopic procedures are the primary diagnostic tools. Small bowel cancers are often diagnosed late due to subtle clinical findings and the limitations of endoscopic imaging. Targeted screening strategies may be beneficial for certain at-risk and symptomatic patient groups. Early surgical intervention offers significant advantages for diagnosed patients.

Diagnostic accuracy of magnetically guided capsule endoscopy with a detachable string for detecting oesophagogastric varices in adults with cirrhosis: prospective multicentre study.

OBJECTIVE: To evaluate the diagnostic accuracy and safety of using magnetically guided capsule endoscopy with a detachable string (ds-MCE) for detecting and grading oesophagogastric varices in adults with cirrhosis. DESIGN: Prospective multicentre diagnostic accuracy study. SETTING: 14 medical centres in China. PARTICIPANTS: 607 adults (>18 years) with cirrhosis recruited between 7 January 2021 and 25 August 2022. Participants underwent ds-MCE (index test), followed by oesophagogastroduodenoscopy (OGD, reference test) within 48 hours. The participants were divided into development and validation cohorts in a ratio of 2:1. MAIN OUTCOME MEASURES: The primary outcomes were the sensitivity and specificity of ds-MCE in detecting oesophagogastric varices compared with OGD. Secondary outcomes included the sensitivity and specificity of ds-MCE for detecting high risk oesophageal varices and the diagnostic accuracy of ds-MCE for detecting high risk oesophagogastric varices, oesophageal varices, and gastric varices. RESULTS: ds-MCE and OGD examinations were completed in 582 (95.9%) of the 607 participants. Using OGD as the reference standard, ds-MCE had a sensitivity of 97.5% (95% confidence interval 95.5% to 98.7%) and specificity of 97.8% (94.4% to 99.1%) for detecting oesophagogastric varices (both P<0.001 compared with a prespecified 85% threshold). When using the optimal 18% threshold for luminal circumference of the oesophagus derived from the development cohort (n=393), the sensitivity and specificity of ds-MCE for detecting high risk oesophageal varices in the validation cohort (n=189) were 95.8% (89.7% to 98.4%) and 94.7% (88.2% to 97.7%), respectively. The diagnostic accuracy of ds-MCE for detecting high risk oesophagogastric varices, oesophageal varices, and gastric varices was 96.3% (92.6% to 98.2%), 96.9% (95.2% to 98.0%), and 96.7% (95.0% to 97.9%), respectively. Two serious adverse events occurred with OGD but none with ds-MCE. CONCLUSION: The findings of this study suggest that ds-MCE is a highly accurate and safe diagnostic tool for detecting and grading oesophagogastric varices and is a promising alternative to OGD for screening and surveillance of oesophagogastric varices in patients with cirrhosis. TRIAL REGISTRATION: ClinicalTrials.gov NCT03748563.

Age Is a Risk Factor for Gastroscopy-Assisted Capsule Endoscopy in Children.

BACKGROUND/AIMS: The aim of this study was to explore the risk factors for the incidence of gastroscopy-assisted capsule endoscopy and the small bowel transit time in pediatric patients who underwent capsule endoscopy examination. MATERIALS AND METHODS: A retrospective analysis was performed to analyze the clinical data collected from pediatric patients who underwent capsule endoscopy examination. RESULTS: A total of 239 pediatric patients were enrolled in this study. About 196 (82.0%) patients completed the entire small bowel capsule endoscopy examination, while 3 (1.3%) patients were subjected to capsule retention. Only age, not gender, height, body weight, body mass index, chief complaint, and intestinal preparation medications, has been identified as a risk factor for the incidence of gastroscopy-assisted capsule endoscopy (P < .05) by multivariate logistic regression. Further analysis showed that the small bowel transit time in the self-swallowed group was shorter than that in the gastroscopy-assisted group, while no significant difference was obtained in other factors, including intestinal preparation medications, metoclopramide, and lesions in the small intestine, which did not significantly affect small bowel transit time compared with the corresponding control group (P > .05). CONCLUSION: A comprehensive assessment is required before performing capsule endoscopy, because age has been identified as a critical risk factor for the incidence of gastroscopy-assisted capsule endoscopy in pediatric patients.

STRUCTURAL EVALUATION OF INFLAMMATORY BOWEL DISEASE COMPREHENSIVE CARE UNITS IN BRAZIL.

BACKGROUND: The most efficient way to prevent complications from inflammatory bowel disease (IBD) is to provide patients with optimized care. Nonetheless, in Brazil, there is no validated methodology for evaluating health services recognized as comprehensive care units (CCU), making it difficult to assess the quality of care provided. OBJECTIVE: To understand the current scenario, map the distribution of centers and identify strengths and weaknesses, considering local and regional characteristics. METHODS: The study was carried out in three phases. Initially, the Brazilian Organization for Crohn's disease and colitis (GEDIIB) developed 22 questions to characterize CCU in Brazil. In the second phase, all GEDIIB members were invited to respond to the survey with the 11 questions considered most relevant. In the last phase, an interim analysis of the results was performed, using the IBM SPSS Statistics v 29.0.1.0 software. Descriptive statistics were used to characterize the center's profile. The chi-square test was used to compare categorical variables. RESULTS: There were 53 responses from public centers (11 excluded). Most centers were concentrated in the Southeastern (n=22/52.4%) and only 1 (2.4%) in the Northern region of Brazil. Thirty-nine centers (92.9%) perform endoscopic procedures, but only 9 (21.4%) have access to enteroscopy and/or small bowel capsule endoscopy. Thirty-three centers (78.6%) offer infusion therapy locally, 26 (61.9%) maintain IBD patient records, 13 (31.0%) reported having an IBD nurse, 34 (81.0%) have specific evidence-based protocols and only 7 (16.7%) have a patient satisfaction methodology. In the private scenario there were 56 responses (10 excluded). There is also a concentration in the Southeastern and Southern regions. Thirty-nine centers (84.8%) have access to endoscopic procedures and 19 perform enteroscopy and/or small bowel capsule endoscopy, more than what is observed in the public environment. Infusion therapy is available in 24 centers (52.2%). Thirty-nine centers (84.8%) maintain a specific IBD patient database, 17 (37%) have an IBD nurse, 36 (78.3%) have specific evidence-based protocols, and 22 (47. 8%) apply a patient satisfaction methodology. CONCLUSION: IBD CCU in Brazil were mainly located in the Southeastern and Southern regions of the country. Most centers have dedicated multidisciplinary teams and IBD specialists. There is still a current need to improve the proportion of IBD nurses in IBD care in Brazil. BACKGROUND: •In Brazil, there is no validated methodology for evaluating health services recognized as comprehensive care units (CCU), making it difficult to assess the quality of care provided. BACKGROUND: •Most CCU were concentrated in the Southeast region and only one (2.4%) in the Northeast region of Brazil. This pattern follows the epidemiological trends of IBD in the country. BACKGROUND: •There is still difficulty in accessing enteroscopy and/or small bowel capsule endoscopy in the public health system. BACKGROUND: •Most centers have dedicated multidisciplinary teams and IBD specialist doctors. BACKGROUND: •There is still a current need to improve the proportion of nurses treating IBD in Brazil.

Development and validation of a deep learning system for detection of small bowel pathologies in capsule endoscopy: a pilot study in a Singapore institution.

INTRODUCTION: Deep learning models can assess the quality of images and discriminate among abnormalities in small bowel capsule endoscopy (CE), reducing fatigue and the time needed for diagnosis. They serve as a decision support system, partially automating the diagnosis process by providing probability predictions for abnormalities. METHODS: We demonstrated the use of deep learning models in CE image analysis, specifically by piloting a bowel preparation model (BPM) and an abnormality detection model (ADM) to determine frame-level view quality and the presence of abnormal findings, respectively. We used convolutional neural network-based models pretrained on large-scale open-domain data to extract spatial features of CE images that were then used in a dense feed-forward neural network classifier. We then combined the open-source Kvasir-Capsule dataset (n = 43) and locally collected CE data (n = 29). RESULTS: Model performance was compared using averaged five-fold and two-fold cross-validation for BPMs and ADMs, respectively. The best BPM model based on a pre-trained ResNet50 architecture had an area under the receiver operating characteristic and precision-recall curves of 0.969±0.008 and 0.843±0.041, respectively. The best ADM model, also based on ResNet50, had top-1 and top-2 accuracies of 84.03±0.051 and 94.78±0.028, respectively. The models could process approximately 200-250 images per second and showed good discrimination on time-critical abnormalities such as bleeding. CONCLUSION: Our pilot models showed the potential to improve time to diagnosis in CE workflows. To our knowledge, our approach is unique to the Singapore context. The value of our work can be further evaluated in a pragmatic manner that is sensitive to existing clinician workflow and resource constraints.