Pan-enteric Capsule Endoscopy to Characterize Crohn's Disease Phenotypes and Predict Clinical Outcomes in Children and Adults: The Bomiro Study.

BACKGROUND: Pan-enteric capsule endoscopy (PCE) provides useful information for the management of Crohn's disease (CD), especially in children. No study has evaluated the ability of PCE to characterize CD phenotypes and outcomes in children and adults. METHODS: In a prospective multicenter observational study, we recruited patients with CD >6 years from 4 centers in Italy. Patients underwent clinical, biomarker assessment and PCE. Lesions were graded using the PCE system. For each segment, the most common lesion (MCL), the most severe lesion (MSL), and the extent of involvement were defined. Disease severity, extent, and clinical outcomes were compared between children and adults. A logistic regression analysis was used to identify predictive factors for negative outcomes in both age groups. RESULTS: One hundred ninety-four consecutive patients (adults/children: 144/50) were evaluated for a total of 249 procedures. Children were more likely to have extensive disease, particularly in the colon. Higher MCL scores were independently associated with treatment escalation (odds ratio [OR], 4.09; 95% CI, 1.80-9.25; P = .001), while >30% disease extent was more indicative of clinical and endoscopic relapse (OR, 2.98; 1.26-7.08; P = .013). Disease extent was the only factor associated with endoscopic recurrence in children (OR, 4.50; 95% CI, 1.47-13.77; P = .008), while severe lesions in adults provided a better predictor of treatment escalation (OR, 4.31; 95% CI, 1.52-12.1; P = .006). Postexamination, PCE contributed to a change of therapy in 196/249 (79%) of the procedures. CONCLUSIONS: PCE allowed the characterization of CD phenotypes in children and adults by assessing disease severity and extent, which are of different importance in predicting clinical outcomes in these age groups.

The study introduces the pan-enteric capsule (PCE) as an efficient tool for assessing Crohn's disease in pediatric and adult patients, providing valuable insights into disease extent and severity, influencing treatment decisions, and improving patient care.

Treatment options for gastrointestinal bleeding blue rubber bleb nevus syndrome: Systematic review.

OBJECTIVES: Blue rubber bleb nevus syndrome (BRBNS) is a rare challenging cause of gastrointestinal bleeding. We performed a systematic review of case reports and case series on BRBNS to gather information on the treatment options currently available. METHODS: All studies reporting a case of BRBNS in humans were evaluated. Papers were ruled out if CARE criteria and explanations on patient's selection, ascertainment, causality, and reporting were not respected or identified. PROSPERO 2021 CRD 42021286982. RESULTS: Blue rubber bleb nevus syndrome was treated in 106 cases from 76 reports. 57.5% of the population was under 18 years old, and up to 50% of the cases reported a previous treatment. Clinical success was achieved in 98 patients (92.4%). Three main types of interventions were identified: systemic drug therapy, endoscopy, and surgery. After BRBNS recurrence or previous therapy failure, systemic drug therapy emerged as a preferred second-line treatment over endoscopy (P = 0.01), but with a higher rate of reported adverse events when compared with surgery and endoscopy (P < 0.001). Endoscopic treatment was associated with a higher number of required sessions to achieve complete eradication when compared with surgery (P < 0.001). No differences between the three main areas were found in the overall follow-up time (P = 0.19) or in the recurrence rate (P = 0.45). CONCLUSION: Endoscopy, surgery, and systemic drug therapy are feasible treatment options for BRBNS. Systemic drug therapy was the favorite second-line treatment after endoscopic failure or recurrence of BRBNS, but adverse events were more frequently reported.

The carbon cost of inappropriate endoscopy.

BACKGROUND AND AIMS: Digestive endoscopy is a resource-intensive activity with a conspicuous carbon footprint and an estimated rate of inappropriateness. However, the carbon costs of inappropriate endoscopic procedures still remain obscure. Here we evaluated the environmental impact of inappropriate endoscopic examinations. METHODS: We calculated the carbon cost of a standard endoscopic procedure (EGD and colonoscopy [CLS]), taking into account the items (eg, disposable materials, personal protective equipment) and energy required for the endoscopy procedure itself and the cleaning process. The rates of inappropriateness and the mortality cost of carbon (MCC) of endoscopic examinations in different scenarios were calculated. RESULTS: EGD and CLS presented a carbon cost of 5.43 kg and 6.71 kg of CO2, respectively. Different scenarios were evaluated, according to the number of endoscopic procedures performed in Italy per 1000 inhabitants and the reported data on their inappropriateness. The carbon cost of inappropriate EGD and CLS in Italy was 4133 CO2 metric tons per year (MCC, .93), ranging from 3527 to 4749, and equivalent to 1,760,446 L of gasoline consumed. Applying the same data to the European population, the estimated carbon footprint of inappropriate digestive endoscopy in Europe was 30,804 metric tons. CONCLUSIONS: The environmental impact of inappropriate endoscopic procedures in Europe is remarkable. These results highlight the need to adopt novel strategies aimed at reducing both the carbon footprint of digestive endoscopy and the rate of inappropriate procedures.

Can artificial intelligence replace endoscopists when assessing mucosal healing in ulcerative colitis? A systematic review and diagnostic test accuracy meta-analysis.

BACKGROUNDS AND AIMS: Mucosal healing (MH) in inflammatory bowel diseases (IBD) is an important landmark for clinical decision making. Artificial intelligence systems (AI) that automatically deliver the grade of endoscopic inflammation may solve moderate interobserver agreement and the need of central reading in clinical trials. METHODS: We performed a systematic review of EMBASE and MEDLINE databases up to 01/12/2022 following PRISMA and the Joanna Briggs Institute methodologies to answer the following question: "Can AI replace endoscopists when assessing MH in IBD?". The research was restricted to ulcerative colitis (UC), and a diagnostic odds ratio (DOR) meta-analysis was performed. Risk of bias was evaluated with QUADAS-2 tool. RESULTS: A total of 21 / 739 records were selected for full text evaluation, and 12 were included in the meta-analysis. Deep learning algorithms based on convolutional neural networks architecture achieved a satisfactory performance in evaluating MH on UC, with sensitivity, specificity, DOR and SROC of respectively 0.91(CI95 %:0.86-0.95);0.89(CI95 %:0.84-0.93);92.42(CI95 %:54.22-157.53) and 0.957 when evaluating fixed images (n = 8) and 0.86(CI95 %:0.75-0.93);0.91(CI95 %:0.87-0.94);70.86(CI95 %:24.63-203.86) and 0.941 when evaluating videos (n = 6). Moderate-high levels of heterogeneity were noted, limiting the quality of the evidence. CONCLUSIONS: AI systems showed high potential in detecting MH in UC with optimal diagnostic performance, although moderate-high heterogeneity of the data was noted. Standardised and shared AI training may reduce heterogeneity between systems.

Validation of a new optical diagnosis training module to improve dysplasia characterization in inflammatory bowel disease: a multicenter international study.

BACKGROUND AND AIMS: Inflammatory bowel disease (IBD) increases risk of dysplasia and colorectal cancer. Advanced endoscopic techniques allow for the detection and characterization of IBD dysplastic lesions, but specialized training is not widely available. We aimed to develop and validate an online training platform to improve the detection and characterization of colonic lesions in IBD: OPtical diagnosis Training to Improve dysplasia Characterization in Inflammatory Bowel Disease (OPTIC-IBD). METHODS: We designed a web-based learning module that includes surveillance principles, optical diagnostic methods, approach to characterization, and classifications of colonic lesions using still images and videos. We invited gastroenterologists from Canada, Italy, and the United Kingdom with a wide range of experience. Participants reviewed 24 educational videos of IBD colonic lesions, predicted histology, and rated their confidence. The primary endpoint was to improve accuracy in detecting dysplastic lesions after training on the platform. Furthermore, participants were randomized 1:1 to get additional training or not, with a final assessment occurring after 60 days. Diagnostic performance for dysplasia and rater confidence were measured. RESULTS: A total of 117 participants completed the study and were assessed for the primary endpoint. Diagnostic accuracy improved from 70.8% to 75.0% (P = .002) after training, with the greatest improvements seen in less experienced endoscopists. Improvements in both accuracy and confidence were sustained after 2 months of assessment, although the group randomized to receive additional training did not improve further. Similarly, participants' confidence in characterizing lesions significantly improved between before and after the course (P < .001), and it was sustained after 2 months of assessment. CONCLUSIONS: The OPTIC-IBD training module demonstrated that an online platform could improve participants' accuracy and confidence in the optical diagnosis of dysplasia in patients with IBD. The training platform can be widely available and improve endoscopic care for people with IBD. (Clinical trial registration number: NCT04924543.).

Clinical impact of videocapsule endoscopy and device-assisted enteroscopy in non-bleeding small bowel lesions.

Background: Videocapsule endoscopy (VCE) and double-balloon enteroscopy (DBE) are part of the diagnostic and therapeutic work-up of indications other than suspected small bowel bleeding (OSBB). The literature is currently lacking studies describing these procedures in this particular setting. Objectives: We assessed the clinical impact of VCE and DBE in a large monocentric cohort of OSBB patients, as compared to a control group of suspected small bowel bleeding (SSBB) patients who underwent enteroscopy over the same period. Design: Monocentric, retrospective, cohort study. Methods: We collected the data of consecutive patients with OSBB undergoing VCE and/or DBE from March 2001 to July 2020. The demographic and clinical parameters of the patients, technical characteristics, and adverse events for each procedure were collected. The impact of VCE and DBE was defined in terms of diagnostic yield (DY). The patients were subdivided according to the main indication into four groups: celiac disease, Crohn's disease (CD), neoplasia, and persistent gastrointestinal symptoms. Results: A total of 611 VCEs and 387 DBEs were performed for OSBB. The main indications were complicated celiac disease and CD. The DYs of VCE and DBE overall were 53 and 61.7%, respectively, with some variance among the four groups. We report no statistical differences in the DY of VCE and DBE in SSBB vs OSBB (57.7% vs 53%, p = 0.0859 and 68.8% vs 61.7%, p = 0.0582, respectively). OSBB patients were significantly younger than those with SSBB. However, similarly to SSBB (k = 0.059), poor agreement between the enteroscopic techniques was found in the OSBB population (k = 0.109). The safety of both procedures in OSBB was comparable to that in SSBB patients. Conclusion: VCE and DBE are effective and safe in suspected OSBB, where their role is similar to that in SSBB, their main indication.

Personalize, participate, predict, and prevent: 4Ps in inflammatory bowel disease.

Inflammatory bowel disease (IBD), which includes Crohn's disease (CD) and ulcerative colitis (UC), is a complex, immune-mediated, disorder which leads to several gastrointestinal and systemic manifestations determining a poor quality of life, disability, and other negative health outcomes. Our knowledge of this condition has greatly improved over the last few decades, and a comprehensive management should take into account both biological (i.e., disease-related, patient-related) and non-biological (i.e., socioeconomic, cultural, environmental, behavioral) factors which contribute to the disease phenotype. From this point of view, the so called 4P medicine framework, including personalization, prediction, prevention, and participation could be useful for tailoring ad hoc interventions in IBD patients. In this review, we discuss the cutting-edge issues regarding personalization in special settings (i.e., pregnancy, oncology, infectious diseases), patient participation (i.e., how to communicate, disability, tackling stigma and resilience, quality of care), disease prediction (i.e., faecal markers, response to treatments), and prevention (i.e., dysplasia through endoscopy, infections through vaccinations, and post-surgical recurrence). Finally, we provide an outlook discussing the unmet needs for implementing this conceptual framework in clinical practice.

Artificial Intelligence Enabled Histological Prediction of Remission or Activity and Clinical Outcomes in Ulcerative Colitis.

BACKGROUND & AIMS: Microscopic inflammation has significant prognostic value in ulcerative colitis (UC); however, its assessment is complex with high interobserver variability. We aimed to develop and validate an artificial intelligence (AI) computer-aided diagnosis system to evaluate UC biopsies and predict prognosis. METHODS: A total of 535 digitalized biopsies (273 patients) were graded according to the PICaSSO Histologic Remission Index (PHRI), Robarts, and Nancy Histological Index. A convolutional neural network classifier was trained to distinguish remission from activity on a subset of 118 biopsies, calibrated on 42 and tested on 375. The model was additionally tested to predict the corresponding endoscopic assessment and occurrence of flares at 12 months. The system output was compared with human assessment. Diagnostic performance was reported as sensitivity, specificity, prognostic prediction through Kaplan-Meier, and hazard ratios of flares between active and remission groups. We externally validated the model in 154 biopsies (58 patients) with similar characteristics but more histologically active patients. RESULTS: The system distinguished histological activity/remission with sensitivity and specificity of 89% and 85% (PHRI), 94% and 76% (Robarts Histological Index), and 89% and 79% (Nancy Histological Index). The model predicted the corresponding endoscopic remission/activity with 79% and 82% accuracy for UC endoscopic index of severity and Paddington International virtual ChromoendoScopy ScOre, respectively. The hazard ratio for disease flare-up between histological activity/remission groups according to pathologist-assessed PHRI was 3.56, and 4.64 for AI-assessed PHRI. Both histology and outcome prediction were confirmed in the external validation cohort. CONCLUSION: We developed and validated an AI model that distinguishes histologic remission/activity in biopsies of UC and predicts flare-ups. This can expedite, standardize, and enhance histologic assessment in practice and trials.

Factors influencing the presence of potentially explosive gases during colonoscopy: Results of the SATISFACTION study.

This study tested the hypothesis that bowel preparation with mannitol should not affect the colonic concentration of H2 and CH4 . Therefore, the SATISFACTION study, an international, multicenter, randomized, parallel-group phase II-III study investigated this issue. The phase II dose-finding part of the study evaluated H2 , CH4 , and O2 concentrations in 179 patients randomized to treatment with 50 g, 100 g, or 150 g mannitol. Phase III of the study compared the presence of intestinal gases in 680 patients randomized (1:1) to receive mannitol 100 g in single dose or a standard split-dose 2 L polyethylene glycol (PEG)-Asc preparation (2 L PEG-Asc). Phase II results showed that mannitol did not influence the concentration of intestinal gases. During phase III, no patient in either group had H2 or CH4 concentrations above the critical thresholds. In patients with H2 and/or CH4 levels above detectable concentrations, the mean values were below the risk thresholds by at least one order of magnitude. The results also highlighted the effectiveness of standard washing and insufflation maneuvers in removing residual intestinal gases. In conclusion, bowel cleansing with mannitol was safe as the concentrations of H2 and CH4 were the same as those found in patients prepared with 2 L PEG-Asc. In both groups, the concentrations of gases were influenced more by the degree of cleansing achieved and the insufflation and washing maneuvers performed than by the preparation used for bowel cleansing. The trial protocol was registered with ClinicalTrials.gov (https://clinicaltrials.gov/ct2/show/NCT04759885) and with EudraCT (eudract_number: 2019-002856-18).

Risk factors for inadequate bowel preparation in patients using high- and low-volume cleansing products.

INTRODUCTION: Bowel preparation is crucial for colonoscopy completeness and lesions detection. Today, several cleansing products are equally recommended by guidelines, irrespective of patients' characteristics. Identification of preparation-specific risk factors for inadequate bowel preparation may lead to a personalized prescription of cleansing products to refine patients' tolerance and improve endoscopic outcomes. METHODS: We prospectively enrolled consecutive outpatients referred for colonoscopy using either a high-volume [HV: 4 l polyethylene glycol (PEG)] or a low-volume (LV: 2 l PEG + bisacodyl) preparation. Day-before regimen or split-dose regimen was used for morning or afternoon colonoscopies, respectively. Univariate and multivariate analyses were conducted to identify risk factors related to inadequate bowel preparation, according to the Boston bowel preparation scale for HV and LV preparations. RESULTS: We enrolled 2040 patients, of which 1815 were included in the final analysis (average age 60.6 years, 50.2% men). Half of them (52%) used LV preparation. Adequate preparation was achieved by 87.6% without differences between the HV and LV groups (89.2% vs. 86.6%; P = 0.098). The use of day-before regimen and incomplete assumption of PEG were independent predictors of poor visibility for either HV or LV preparation. However, different specific risk factors for HV [diabetes: odds ratio (OR), 3.81; 95% confidence interval (CI), 1.91-7.58; low level of instruction: OR, 1.95; 95% CI, 1.11-3.44; and previous abdominal surgery: OR, 2.27; 95% CI, 1.20-4.30] and for LV (heart disease: OR, 2.06; 95% CI, 1.09-3.88; age > 65 years: OR, 1.51; 95% CI, 1.01-2.27) preparations were identified. CONCLUSION: Day-before preparation and incomplete assumption of the purgative agents affect bowel visibility irrespective of the preparation volume. LV should be preferred to HV preparations in patients with diabetes, low level of instruction, and previous abdominal surgery, whereas an HV preparation should be preferred in patients with heart disease and in older patients.

Effectiveness of double-balloon enteroscopy-assisted endoscopic retrograde cholangiopancreatography (DBE-ERCP): A multicenter real-world study.

BACKGROUND AND AIMS: To investigate the effectiveness of double-balloon enteroscope-assisted retrograde cholangiopancreatography (DBE-ERCP) in patients with gastrointestinal surgically altered anatomy (SAA). METHODS: From May 2013 to October 2021, all consecutive patients undergoing DBE-ERCP in three gastroenterological referral centers in Northern Italy were enrolled in the study. Patients were assessed regarding their medical history, previous surgery, time from previous surgery to the DBE-ERCP procedure, and the success or failure of DBE-ERCP. RESULTS: Fifty-three patients (60% men, median age 65 (23-89) years) undergoing 67 DBE-ERCP procedures (1-3 DBE-ERCP per patient) were enrolled. Reasons for SAA included orthotopic liver transplantation (23%), ulcers (15%), malignancies (43%), difficult cholecystectomy (17%), and other causes (2%). Types of surgery included Roux-en-Y biliodigestive anastomosis (45%), Roux-en-Y gastrectomy (32%), pancreaticoduodenectomy (17%), and Billroth II gastrectomy (6%). The overall DBE-ERCP success rate was 86%. The type of surgery, indications, and the length of time between previous surgery and DBE-ERCP were not statistically associated with DBE-ERCP success. The DBE-ERCP success rate increased from 2018 to 2021. CONCLUSIONS: DBE-ERCP is a successful procedure in challenging patients with SAA. The improvement in results over time indicates the necessity of adequate training and of centralizing patients in referral centers.

A virtual chromoendoscopy artificial intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in ulcerative colitis.

BACKGROUND: Endoscopic and histological remission (ER, HR) are therapeutic targets in ulcerative colitis (UC). Virtual chromoendoscopy (VCE) improves endoscopic assessment and the prediction of histology; however, interobserver variability limits standardized endoscopic assessment. We aimed to develop an artificial intelligence (AI) tool to distinguish ER/activity, and predict histology and risk of flare from white-light endoscopy (WLE) and VCE videos. METHODS: 1090 endoscopic videos (67 280 frames) from 283 patients were used to develop a convolutional neural network (CNN). UC endoscopic activity was graded by experts using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Paddington International virtual ChromoendoScopy ScOre (PICaSSO). The CNN was trained to distinguish ER/activity on endoscopy videos, and retrained to predict HR/activity, defined according to multiple indices, and predict outcome; CNN and human agreement was measured. RESULTS: The AI system detected ER (UCEIS ≤ 1) in WLE videos with 72 % sensitivity, 87 % specificity, and an area under the receiver operating characteristic curve (AUROC) of 0.85; for detection of ER in VCE videos (PICaSSO ≤ 3), the sensitivity was 79 %, specificity 95 %, and the AUROC 0.94. The prediction of HR was similar between WLE and VCE videos (accuracies ranging from 80 % to 85 %). The model's stratification of risk of flare was similar to that of physician-assessed endoscopy scores. CONCLUSIONS: Our system accurately distinguished ER/activity and predicted HR and clinical outcome from colonoscopy videos. This is the first computer model developed to detect inflammation/healing on VCE using the PICaSSO and the first computer tool to provide endoscopic, histologic, and clinical assessment.

Clinical features of type 1 and 2 refractory celiac disease: Results from a large cohort over a decade.

OBJECTIVES: Refractory celiac disease (RCeD) is a rare complication of celiac disease (CeD) with a severe prognosis. We describe a cohort of patients with RCeD, their clinical and histological features at diagnosis, after therapy and at lymphoma onset, and the rate and causes of death over a 17-year follow-up. METHODS: We retrospectively enrolled RCeD-I and RCeD-II patients attending our center between January 2002 and October 2019. Medical data were collected at diagnosis and during monitoring. Response to therapy, changes in RCeD molecular markers, number of hospitalizations, discharge diagnosis, and cause and date of death were evaluated. The control cohort consisted of 1015 responsive CeD patients. RESULTS: Compared with RCeD-I, RCeD-II more frequently exhibits diarrhea (83 vs 64%), anemia (61 vs 50%), hypoalbuminemia (70 vs 21%), parenteral nutrition need (48 vs 7%), ulcerative jejuno-ileitis (7 vs 39%), and extended small intestinal atrophy (62 vs 21%). One RCeD-I and six RCeD-II patients developed lymphoma. Ten RCeD-II patients died, four from lymphoma progression. Among RCeD-II patients, atrophy extension was the only parameter correlated with hypoalbuminemia and mortality. CONCLUSIONS: Clinical severity, response to therapy, and mortality differ between RCeD-I and RCeD-II. Atrophy extension, evaluated at capsule endoscopy, was associated with disease severity and mortality.

Enteroscopy in diagnosis and treatment of small bowel bleeding: A Delphi expert consensus.

BACKGROUND: Enteroscopy plays an important role in the management of small bowel bleeding. However, current guidelines are not specifically designed for small bowel bleeding and recommendations from different international societies do not always align. Consequently, there is heterogeneity in the definitions of clinical entities, clinical practice policies, and adherence to guidelines among clinicians. This represents an obstacle to providing the best patient care and to obtain homogeneous data for clinical research. AIMS: The aims of the study were to establish a consensus on the definitions of bleeding entities and on the role of enteroscopy in the management of small bowel bleeding using a Delphi process. METHODS: A core group of eight experts in enteroscopy identified five main topics of small bowel bleeding management and drafted statements on each topic. An expert panel of nine gastroenterologists participated in three rounds of the Delphi process, together with the core group. RESULTS: A total of 33 statements were approved after three rounds of Delphi voting. CONCLUSION: This Delphi consensus proposes clear definitions and a unifying strategy to standardize the management of small bowel bleeding. Furthermore, it provides a useful guide in daily practice for both clinical and technical issues of enteroscopy.

Key research questions for implementation of artificial intelligence in capsule endoscopy.

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.