(1) Background: Predicting which patients with upper gastro-intestinal bleeding (UGIB) will receive intervention during urgent endoscopy can allow for better triaging and resource utilization but remains sub-optimal. Using machine learning modelling we aimed to devise an improved endoscopic intervention predicting tool. (2) Methods: A retrospective cohort study of adult patients diagnosed with UGIB between 2012–2018 who underwent esophagogastroduodenoscopy (EGD) during hospitalization. We assessed the correlation between various parameters with endoscopic intervention and examined the prediction performance of the Glasgow-Blatchford score (GBS) and the pre-endoscopic Rockall score for endoscopic intervention. We also trained and tested a new machine learning-based model for the prediction of endoscopic intervention. (3) Results: A total of 883 patients were included. Risk factors for endoscopic intervention included cirrhosis (9.0% vs. 3.8%, p = 0.01), syncope at presentation (19.3% vs. 5.4%, p < 0.01), early EGD (6.8 h vs. 17.0 h, p < 0.01), pre-endoscopic administration of tranexamic acid (TXA) (43.4% vs. 31.0%, p < 0.01) and erythromycin (17.2% vs. 5.6%, p < 0.01). Higher GBS (11 vs. 9, p < 0.01) and pre-endoscopy Rockall score (4.7 vs. 4.1, p < 0.01) were significantly associated with endoscopic intervention; however, the predictive performance of the scores was low (AUC of 0.54, and 0.56, respectively). A combined machine learning-developed model demonstrated improved predictive ability (AUC 0.68) using parameters not included in standard GBS. (4) Conclusions: The GBS and pre-endoscopic Rockall score performed poorly in endoscopic intervention prediction. An improved predictive tool has been proposed here. Further studies are needed to examine if predicting this important triaging decision can be further optimized.

Crohn’s disease (CD) is a chronic inflammatory disorder that may involve the gastrointestinal tract from the mouth to the anus. Habitual disease monitoring is highly important during disease management, aiming to identify and treat disease exacerbations, in order to avoid immediate and future complications. Currently, ilio-clonoscopy is the gold standard for mucosal assessment. However, the procedure is invasive, involves sedation and allows for visualization of the colon and only a small part of the terminal ileum, while most of the small bowel is not visualized. Since CD may involve the whole length of the small bowel, the disease extent might be underestimated. Capsule endoscopy (CE) provides a technology that can screen the entire bowel in a non-invasive procedure, with minimal side effects. In recent years, this technique has gained in popularity for CD evaluation and monitoring. When CE was first introduced, two decades ago, the fear of possible capsule retention in the narrowed inflamed bowel lumen limited its use in CD patients, and a known CD located at the small bowel was even regarded as a relative contraindication for capsule examination. However, at present, as experience using CE in CD patients has accumulated, this procedure has become one of the accepted tools for disease diagnosis and monitoring. In our current review, we summarize the historic change in the indications and contraindications for the usage of capsule endoscopy for the evaluation of CD, and discuss international recommendations regarding CE’s role in CD diagnosis and monitoring.

Background: Urinary tract infection (UTI) is the most common urologic complication among patients with inflammatory bowel disease (IBD). However, data regarding UTI outcomes in this population are scarce. We aimed to evaluate adverse outcomes of UTI among patients with IBD. Methods: This was a retrospective cohort study of consecutive adult patients who visited the emergency room (ER) at Sheba Medical Center due to a UTI between 2012 and 2018. Data included demographic and clinical variables. UTI cases were extracted using ICD-10 coding. Results: Of 21,808 (ER) visits with a UTI, 122 were IBD patients (Crohn’s disease—52, ulcerative colitis—70). Contrary to non-IBD subjects, patients with IBD had higher rates of hospitalization, acute kidney injury (AKI) and 30 day-recurrent hospitalization (59.3% vs. 68.9%, p = 0.032; 4.6% vs. 13.9%, p < 0.001; 7.3% vs. 15.6%, p = 0.001, respectively). Among patients with IBD, advanced age (p = 0.005) and recent hospitalization (p = 0.037) were associated with increased risk for hospitalization, while hydronephrosis (p = 0.005), recent hospitalization (p = 0.011) and AKI (p = 0.017) were associated with increased 30-day recurrent hospitalization. Neither immunosuppressants nor biologics were associated with UTI outcomes among patients with IBD. Conclusions: Patients with IBD treated for a UTI had higher rates of hospitalization, AKI and 30-day recurrent hospitalization than non-IBD patients. No association was observed between immunosuppressants or biologics and UTI outcomes.

Background: Small bowel video capsule endoscopy (SB-VCE) assesses mucosal inflammation in Crohn’s disease (CD), while intestinal ultrasound (IUS) examines transmural involvement. We aimed to correlate SB-VCE with IUS in evaluating active CD and monitoring treatment response over time. Methods: Patients with active SB-CD who initiated biologics were prospectively followed with fecal calprotectin (FC), SB-VCE, and IUS at baseline and after 14 and 52 weeks. The Lewis score (LS), Limberg index (LI), and terminal ileum bowel wall thickness (TI-BWT) were documented, and the International Bowel Ultrasound Segmental Activity Score (IBUS-SAS) was retrospectively calculated. Biochemical, endoscopic, and ultrasonographic remission were defined as FC < 150 μg/g, LS < 135, and LI < 2 + TI-BWT ≤ 3 mm, respectively. A therapeutic response for each index was defined as a 25% reduction compared to baseline. Results: Seventy-one patients were included (median age: 30 years [23-43], 49.3% male). The median interval between SB-VCE and IUS was 3 days (0-25). Initially, the LS strongly correlated with TI-BWT (r = 0.647, P < .001), LI (r = 0.597, P < .001), and IBUS-SAS (r = 0.647, P < .001), but these correlations weakened over time (TI-BWT: r = 0.344, P = .002; LI: r = 0.471, P = .001; IBUS-SAS: r = 0.236, P = .122). Moderate agreement was found between ultrasonographic and endoscopic treatment responses (LS and TI-BWT: K = 0.51, P = .015; LS and LI: K = 0.44, P = .063), with fair agreement for remission (K = 0.27, P = .006). TI-BWT best cutoffs for mild (LS ≥ 135) and moderate-to-severe (LS ≥ 790) inflammation were 2.25 mm and 3.6 mm, respectively Conclusions: IUS measures are strongly correlated with VCE-inflammatory LS in active CD and may provide an assessment of endoscopic response and remission over time.

Infliximab and vedolizumab are effective treatments for inflammatory bowel disease (IBD), although associated with adverse events (AE). While low or non-existent drug levels and positive antidrug antibodies have been associated with therapeutic failure, there is no clear association between higher drug levels and AE. A cross-sectional study consisting of Crohn’s disease (CD) and ulcerative colitis (UC) patients receiving infliximab or vedolizumab at the Sheba Medical Center was performed. Patients completed a questionnaire regarding AEs related to biological therapy. Serum trough levels obtained on the same day were analyzed. Objective measures of outcomes were retrieved from medical records. Questionnaires were completed by infliximab (n = 169) and vedolizumab (n = 88)-treated therapy patients. Higher infliximab levels were only numerically associated with the occurrence of at least one AE (p = 0.08). When excluding fatigue and abdominal pain, higher infliximab levels were statistically associated with the occurrence of at least one AE (p = 0.03). Vedolizumab drug levels > 18 μg/mL were also linked with the occurrence of more AEs. No specific association was observed between the increased levels of either infliximab or vedolizumab and specific AEs (neurological symptoms, upper GI symptoms, infectious complications, and musculoskeletal symptoms). As significant AEs are very rare, additional multi-center studies are required.