Search

Background: Artificial intelligence (AI) is rapidly infiltrating multiple areas in medicine, with gastrointestinal endoscopy paving the way in both research and clinical applications. Multiple challenges associated with the incorporation of AI in endoscopy are being addressed in recent consensus documents. Objectives: In the current paper, we aimed to map future challenges and areas of research for the incorporation of AI in capsule endoscopy (CE) practice. Design: Modified three-round Delphi consensus online survey. Methods: The study design was based on a modified three-round Delphi consensus online survey distributed to a group of CE and AI experts. Round one aimed to map out key research statements and challenges for the implementation of AI in CE. All queries addressing the same questions were merged into a single issue. The second round aimed to rank all generated questions during round one and to identify the top-ranked statements with the highest total score. Finally, the third round aimed to redistribute and rescore the top-ranked statements. Results: Twenty-one (16 gastroenterologists and 5 data scientists) experts participated in the survey. In the first round, 48 statements divided into seven themes were generated. After scoring all statements and rescoring the top 12, the question of AI use for identification and grading of small bowel pathologies was scored the highest (mean score 9.15), correlation of AI and human expert reading-second (9.05), and real-life feasibility-third (9.0). Conclusion: In summary, our current study points out a roadmap for future challenges and research areas on our way to fully incorporating AI in CE reading. [ABSTRACT FROM AUTHOR]

Background: Bubbles often mask the mucosa during capsule endoscopy (CE). Clinical scores assessing the cleanliness and the amount of bubbles in the small bowel (SB) are poorly reproducible unlike machine learning (ML) solutions. We aimed to measure the amount of bubbles with ML algorithms in SB CE recordings, and compare two polyethylene glycol (PEG)-based preparations, with and without simethicone, in patients with obscure gastro-intestinal bleeding (OGIB). Patients & Methods: All consecutive outpatients with OGIB from a tertiary care center received a PEG-based preparation, without or with simethicone, in two different periods. The primary outcome was a difference in the proportions (%) of frames with abundant bubbles (>10%) along the full-length video sequences between the two periods. SB CE recordings were analyzed by a validated computed algorithm based on a grey-level of co-occurrence matrix (GLCM), to assess the abundance of bubbles in each frame. Results: In total, 105 third generation SB CE recordings were analyzed (48 without simethicone and 57 with simethicone-added preparations). A significant association was shown between the use of a simethicone-added preparation and a lower abundance of bubbles along the SB (p = 0.04). A significantly lower proportion of "abundant in bubbles" frames was observed in the fourth quartile (30.5% vs. 20.6%, p = 0.02). There was no significant impact of the use of simethicone in terms of diagnostic yield, SB transit time and completion rate. Conclusion: An accurate and reproducible computed algorithm demonstrated significant decrease in the abundance of bubbles along SB CE recordings, with a marked effect in the last quartile, in patients for whom simethicone had been added in PEG-based preparations, compared to those without simethicone. [ABSTRACT FROM AUTHOR]

Background: Cleanliness scores in small-bowel capsule endoscopy (SBCE) have poor reproducibility. The aim of this study was to evaluate a neural network-based algorithm for automated assessment of small-bowel cleanliness during capsule endoscopy.Methods: 600 normal third-generation SBCE still frames were categorized as "adequate" or "inadequate" in terms of cleanliness by three expert readers, according to a 10-point scale, and served as a training database. Then, 156 third-generation SBCE recordings were categorized in a consensual manner as "adequate" or "inadequate" in terms of cleanliness; this testing database was split into two independent 78-video subsets for the tuning and evaluation of the algorithm, respectively.Results: Using a threshold of 79 % "adequate" still frames per video to achieve the best performance, the algorithm yielded a sensitivity of 90.3 %, specificity of 83.3 %, and accuracy of 89.7 %. The reproducibility was perfect. The mean calculation time per video was 3 (standard deviation 1) minutes.Conclusion: This neural network-based algorithm allowing automatic assessment of small-bowel cleanliness during capsule endoscopy was highly sensitive and paves the way for automated, standardized SBCE reports. [ABSTRACT FROM AUTHOR]

Résumé: L'endoscopie d'urgence s'adresse à des maladies graves à toute heure de prise en charge. Les indications sont essentiellement le traitement de l'hémorragie digestive et l'extraction des corps étrangers supérieurs. Mais elle peut aussi être nécessaire en cas de volvulus du sigmoïde et de syndrome d'Ogilvie résistant au traitement médical. La plupart des indications urgentes doivent conduire à une endoscopie dans les 24 heures mais, dans de rares cas, le délai doit être de moins de 12 heures voire de moins de 2 heures. Elle est souvent réalisée en dehors des heures ouvrables, la nuit, le week-end et les jours fériés. Elle doit cependant être réalisée dans de bonnes conditions avec une équipe entraînée. La bonne connaissance des indications des endoscopies d'urgence, ainsi que du délai et de ses modalités de réalisation est nécessaire à tout hépato-gastroentérologue pour prendre les bonnes décisions avec les correspondants urgentistes, réanimateurs, radiologues et chirurgiens et conduire à une prise en charge optimale du patient. Emergency endoscopy is mandatory at all times for critically ill patients. Emergency endoscopy is mainly performed for the management of digestive bleeding and for the extraction of foreign bodies. But it may also be necessary in case of sigmoid volvulus and Ogilvie syndrome resistant to medical treatment. Most urgent indications must lead to an endoscopy within 24 hours, and in rare cases within 12 hours or even less than 2 hours. It is therefore often be carried out outside working hours; at night, weekends and holidays. However, it should be performed by a properly trained team in an adequate environment. A knowledge of validated indications for emergency endoscopies, appropriate timing and procedures should therefore be mastered by any hepatogastroenterologist on duty, in order to take the appropriate decisions with emergency intensivists, radiologists and surgeons, and to obtain an optimal care for patients. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) aims to simulate the human intelligence. It is a cognitive science which relies on neurobiology, logical and critical thinking (problem solving, deep learning, neural networks), computing sciences (calculation, internet), and on databases. Big data exploitation (epidemiology, predictive medicine) and "signals" analysis (EKG, EEG, imaging, pathology, dermatology, ophthalmology...) were the first successful application of AI in healthcare, followed by government approval. AI has a vast spectrum of potential applications in digestive endoscopy as well. AI can be used for screening, diagnosis, characterization, treatment, and prognosis evaluation, in a wide array of procedures. The quantity of published work in this field is thriving. Computer-assisted detection and characterization of colonic polyps for instance, were amongst the first successful applications of AI, and should be commercially available shortly. The automated reading of a capsule endoscopy, based on a network of machine learning systems, is also very demonstrative of what AI will be able to accomplish in the next future. It is believed that AI will significantly improve diagnostic performances and thus the quality of care. Today, endoscopists should not only promote this technological revolution, but also address new issues in the field of AI, regarding the respective roles of physicians (focused on ethics and patient-relations) and AI-machines (assistants vs autonomous), as well as responsibility (physicians vs. manufacturing companies), and reimbursement (physician vs manufacturing companies). [ABSTRACT FROM AUTHOR]

Résumé: Les personnes souffrant de maladie inflammatoire chronique de l'intestin (MICI) rapportent que leur santé sexuelle est souvent altérée et insuffisamment abordée lors des consultations médicales ; elles conçoivent moins d'enfants que la population générale. Cette revue vise à apporter au thérapeute une synthèse des outils et informations utiles concernant les dysfonctions de la sexualité et la fertilité des patients atteints de MICI. La dysfonction sexuelle est souvent associée à une altération de l'image corporelle et de la qualité de vie des patients ; ses mécanismes sont multiples. Des troubles anxio-dépressifs sont souvent intriqués. La fertilité est très voisine de celle de la population générale mais quelques cas particuliers doivent être connus des gastroentérologues. Une consultation pré-conceptionnelle apportant des informations simples au couple, répondant à ses questions et corrigeant éventuellement ses croyances erronées est d'une aide démontrée et le maintien de la rémission de la MICI (incluant l'utilisation des traitements médicamenteux) est un élément-clé. ..LAN-EN People with IBD report that their sexual health is often impaired and inadequately addressed during medical consultations; they conceive fewer children than the general population. This review aims to provide the therapist with a synthesis of useful tools and information regarding sexual dysfunction and fertility in IBD patients. Sexual dysfunction is often associated with impaired body image and quality of life for patients; its mechanisms are multiple. Anxio-depressive disorders are often entangled. Fertility is very close to that of the general population, but some special cases must be known to gastroenterologists. A pre-conception consultation providing simple information to the couple, answering their questions and possibly correcting their erroneous beliefs is of proven help and the maintenance of the remission of IBD (including the use of drug treatments) is a key element. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has shown promising results in digestive endoscopy, especially in capsule endoscopy (CE). However, some physicians still have some difficulties and fear the advent of this technology. We aimed to evaluate the perceptions and current sentiments toward the use of AI in CE. An online survey questionnaire was sent to an audience of gastroenterologists. In addition, several European national leaders of the International CApsule endoscopy REsearch (I CARE) Group were asked to disseminate an online survey among their national communities of CE readers (CER). The survey included 32 questions regarding general information, perceptions of AI, and its use in daily life, medicine, endoscopy, and CE. Among 380 European gastroenterologists who answered this survey, 333 (88%) were CERs. The mean average time length of experience in CE reading was 9.9 years (0.5–22). A majority of CERs agreed that AI would positively impact CE, shorten CE reading time, and help standardize reporting in CE and characterize lesions seen in CE. Nevertheless, in the foreseeable future, a majority of CERs disagreed with the complete replacement all CE reading by AI. Most CERs believed in the high potential of AI for becoming a valuable tool for automated diagnosis and for shortening the reading time. Currently, the perception is that AI will not replace CE reading. [ABSTRACT FROM AUTHOR]

Gastrointestinal angiodysplasia are the most common vascular lesions of the digestive tract. Risk factors include age, aortic stenosis (Heyde syndrome), chronic renal failure, cirrhosis and von Willebrandt's disease. Diagnosis is often made in the setting of occult or overt gastrointestinal bleeding. Due to their preferential location in the jejunum and colon, most lesions are diagnosed during upper endoscopy or colonoscopy. In cases where small bowel bleeding is suspected, capsule endoscopy is the gold standard diagnostic exam. A meta-analysis has recently shown that its diagnostic yield is optimal within 48 hours following an overt bleeding episode, and it is recommended to respect this time frame (European Guidelines). Capsule endoscopy is ideal in terms of patient tolerance. However, it is tedious and time-consuming to interpret and requires expertise. In the recent years artificial intelligence applied to capsule endoscopy has developed significantly. Its contribution is now major, with improved diagnostic yield and reduced interpretation time. Argon plasma coagulation during endoscopy is the first-line treatment for gastrointestinal angiodysplasia. Deep enteroscopy is the preferred procedure for ablation of small bowel angiodysplasia. Motorized spiral enteroscopy has enabled easier access to deep small bowel lesions and a shorter procedure time, since it was first used in 2016. However, it has been withdrawn from the market since July 2023, given the occurrence of serious adverse events (perforations). More centres should be equipped with double-ballon enteroscopes in France. The recent results from the randomized controlled OCEAN trial confirm that long-acting release somatostatin analogues (Octreotide) significantly reduce transfusion needs when endoscopic treatment has failed. Thalidomide is also an interesting treatment option, as demonstrated in a randomized control trial published in November 2023, with a reduced recurrence rate of bleeding after 4 months of treatment and during the following year. In the specific case of Heyde syndrome, percutaneous aortic valve replacement (TAVI) also reduces transfusion requirements. [ABSTRACT FROM AUTHOR]