Crohn’s disease and ulcerative colitis remain debilitating disorders, characterized by progressive bowel damage and possible lethal complications. The growing number of applications for artificial intelligence in gastrointestinal endoscopy has already shown great potential, especially in the field of neoplastic and pre-neoplastic lesion detection and characterization, and is currently under evaluation in the field of inflammatory bowel disease management. The application of artificial intelligence in inflammatory bowel diseases can range from genomic dataset analysis and risk prediction model construction to the disease grading severity and assessment of the response to treatment using machine learning. We aimed to assess the current and future role of artificial intelligence in assessing the key outcomes in inflammatory bowel disease patients: endoscopic activity, mucosal healing, response to treatment, and neoplasia surveillance.

Background: The expansion of advanced therapies for inflammatory bowel disease created a lag between the development of these new therapies and their incorporation and use in daily practice. At present, no clear definitions for treatment optimization, treatment failure or criteria to abandon therapy are available. We aimed to centralize criteria for a nonresponse to all available molecules and to summarize guideline principles for treatment optimization. Methods: We conducted a systematic review of studies that reported criteria for the treatment response to all advanced therapies (infliximab, adalimumab, golimumab, ustekinumab, vedolizumab and tofacitinib) in patients with inflammatory bowel disease. Results: Across trials, criteria for a response of both patients with ulcerative colitis and Crohn’s disease are heterogenous. Investigators use different definitions for clinical and endoscopic remission, and endoscopic response and outcomes are assessed at variable time points. Current society guidelines provide heterogenous recommendations on treatment optimization. Most available data on loss of response concern anti-TNF molecules, and newer therapies are not included in the guidelines. Conclusion: The lack of clear definitions and formal recommendations provide the premise for empirical treatment strategies and premature abandonment of therapies.

Background and Aims: MicroRNAs (miR) have altered expression in multiple autoimmune disorders including inflammatory bowel disease. The aim of the study was to assess the tissue and circulating miR-31, miR-200b, and miR-200c expression levels as potential biomarkers for intestinal disease activity in patients with Crohn’s disease (CD). Methods: The study included 45 patients with histopathological confirmed CD and active disease (defined as fecal calprotectin >50 μg/g and Simple Endoscopic Score (SES) of CD >3), and 21 subjects as controls for the validation cohort. Demographic and clinical data, biomarkers (fecal calprotectin), endoscopy data, the expression levels of miR-31, miR-200b, and miR-200c in tissue and serum were assessed (by RT-PCR). Receiver operating characteristic analysis was performed to assess the miR-31, miR-200b, and miR-200c expression levels as potential biomarkers for active CD. Results: Mean fecal calprotectin was 1540±890 μg/g. Mean SES-CD was 8.9±4.2. Tissue and circulating miR- 31 were significantly correlated with fecal calprotectin (r=0.81, r=0.83, p<0.01) and with SES-CD (r=0.82, r=0.79, p<0.01). The expression level of miR-31 was significantly upregulated in CD tissue cases compared to the control tissue samples (6.24±1.57 vs. 3.70±1.44; p <0.01). Similarly, serum miR-31 expression levels in CD patients were significantly upregulated compared to the control serum samples (0.78±0.42 vs. -2.07±1.00; p<0.01). The expression levels of tissue miR-200b and miR-200c were significantly upregulated in CD tissue cases compared to the control tissue samples (-5.25±0.93 vs. -4.69±0.80, p=0.03 for miR-200b, and -0.86±0.96 vs. 0.39±0.66, p<0.01 for miR-200c). Similarly, serum miR-200b and miR-200c expression levels in CD patients were significantly upregulated compared to the control serum samples (p < 0.05). Receiver operating characteristic analysis revealed that the expression levels of the selected miRNAs could help to discriminate active CD patients from healthy controls with very good specificity and sensitivity. Conclusions: Tissue and circulating miR-31, miR-200b, and miR-200c reflect disease activity in CD patients and can be used as biomarkers for active disease.

Background/Aims: Gastrointestinal bleeding is a significant and potentially lethal event. We aimed to review the efficiency and safety of self-assembling peptides for the treatment and prevention of gastrointestinal tract bleeding.Methods: We conducted a systematic search for studies describing the endoscopic use of self-assembling peptides for treatment or prevention of bleeding in the gastrointestinal tract in a parallel, independent fashion. The primary outcomes were rates of successful initial hemostasis, delayed bleeding, and rebleeding. The secondary outcomes were adverse events and ease and volume of gel used.Results: Seventeen studies were analyzed. Overall success rate of self-assembling peptides in gastrointestinal bleeding was 87.7% (38%–100%), regardless of etiology or associated treatments. Rebleeding rate ranged from 0% to 16.2%, with a mean of 4.7%, and overall delayed bleeding rate was 5% (range, 0%–15.9%). Only three adverse events were reported in a pooled number of 815 patients. The volume of gel used varied (0.43 to 3.7 mL) according to indication and type of bleeding.Conclusions: The limited available data on the use of self-assembling peptides in gastrointestinal endoscopy suggest a high efficiency and good safety profile.

Objective: Our aim was to prospectively assess bowel preparation in patients with inflammatory bowel disease (IBD) and to determine the impact of disease-related factors on preparation efficacy because few studies have addressed this issue. Methods: We conducted a retrospective analysis of data collected from a cohort of patients with IBD enrolled at a tertiary center in Bucharest, Romania. Patients were evaluated every 12 months, with each study visit including collection of clinical, biological, and endoscopic data. We reviewed 348 colonoscopies from 169 consecutive patients prospectively followed for a median length of 2 (0–6) years. Results: The median total Boston score and median score per bowel segment in our cohort were optimal at 6 (range 0–9) and 2 (maximum 3), respectively. There was no difference in bowel preparation between patients with endoscopic activity and patients with mucosal healing (median total Boston score 6). Disease- and patient-related parameters did not influence the quality of bowel preparation. Conclusions: The quality of bowel preparation in patients with IBD was optimal for our cohort, and disease-related parameters did not significantly influence preparation efficacy.

Background and Aims: Real-world assessments of efficacy and safety of advanced therapies used for inflammatory bowel disease (IBD) patients are limited. We aimed to report safety, efficacy and treatment persistence of new molecules (infliximab, adalimumab, vedolizumab, tofacitinib, ustekinumab) in a retrospective multicentric national Romanian analysis. Methods: We conducted a nationwide, retrospective observational multicentric study. Data were collected retrospectively from electronic and paper files. Patients who started on one of the five investigated molecules during December 2019-December 2021 were included. The main outcome measures were clinical remission, endoscopic healing, persistence on treatment and safety data. Results: A total of 678 adult patients from 24 Romanian IBD centers with a diagnosis of ulcerative colitis or Crohn’s disease were included. Participants had previously failure to one (268, 39.5%), two (108, 15%) or more treatment lines and only 38% (259) were biologic naïve. In the 24 months study period, most patients were started on vedolizumab (192, 28%), followed by adalimumab, infliximab, ustekinumab and tofacitinib. In biologic-naïve patients, most physicians (72%) preferred anti-TNF treatment as first line biologic (93 patients started on infliximab, 92 on adalimumab), followed by vedolizumab, ustekinumab and tofacitinib. During follow-up, 71% (470, p=0.05) of patients achieved clinical remission and 36% (134, p=0.03) achieved mucosal healing. The 6 months milestone for persistence was reached in 78% (530) of cases. Almost half of patients (47%, 316 patients) persisted on their current treatment for over 12 months. Overall, an adverse reaction was reported for 67 (10.4%) patients, with no lethal events. Conclusions: Population of biologic-experienced IBD patients in Romania is increasing and is becoming more difficult to achieve long-term disease control. Discontinuation rates for advanced therapies are high.