Introduction

Capsule endoscopy (CE) is a minimally invasive and essential tool for assessing small bowel disorders, especially Crohn’s disease. Accurate detection of ulcers and erosions is vital for evaluating disease activity, guiding treatment, and monitoring therapeutic response. Although CE has revolutionized lesion detection, its manual interpretation remains time-consuming and subject to interobserver variability. Recent advances in artificial intelligence (AI), particularly convolutional neural networks (CNNs), offer promising solutions by enhancing diagnostic accuracy, reducing variability, and improving workflow efficiency. This study aimed to develop and validate a robust AI model capable of detecting and distinguishing small bowel ulcers and erosions across multiple CE platforms and clinical centers.

Aims & Methods

In a prospective, multicenter study conducted between January 2021 and April 2024, data were collected from centers in Portugal, Spain, and the United States. Two CE devices—PillCamSB3 and Olympus EC-10—were used to analyze 137 anonymized exams. The AI-assisted readings generated by a deep learning model were compared to standard-of-care (SoC) interpretations, with an expert consensus panel serving as the reference standard. Performance metrics included sensitivity, specificity, positive and negative predictive values (PPV, NPV), and area under the receiver operating characteristic curve (AUROC).

Results

Expert consensus identified ulcers and erosions in 56 patients (40.9%). Compared to the reference standard, SoC readings achieved 60.7% sensitivity, 98.8% specificity, 97.1% PPV, 78.4% NPV, and 83.2% accuracy. In contrast, the AI-assisted model achieved 94.6% sensitivity, 80.2% specificity, 76.8% PPV, 95.6% NPV, and 86.1% accuracy. The AI model was found to be both non-inferior (p < 0.001) and statistically superior (p < 0.001) to SoC. Notably, it identified 68 lesions, nearly double those detected by SoC (35), and demonstrated consistent performance across devices and centers. The mean AI-assisted reading time was 239 seconds (SD 138 seconds) per exam.

Conclusion

The AI-assisted model significantly outperformed conventional SoC in the detection of small bowel ulcers and erosions, achieving higher sensitivity and overall accuracy while substantially reducing reading time. This is the first multicenter validation of an interoperable AI solution for CE, capable of high diagnostic performance across different devices and clinical environments. These findings highlight the potential of AI to transform endoscopic evaluation and management in inflammatory bowel disease.

Introduction

Cholestatic pruritus is common, debilitating and undertreated in patients with primary biliary cholangitis (PBC). Here, we describe the results of GLISTEN (NCT04950127), a Phase 3 study investigating the efficacy and safety of the ileal bile acid transporter inhibitor linerixibat for pruritus in PBC.

Aims & Methods

In this double-blind, randomised, placebo-controlled study, patients with PBC and moderate-to-severe pruritus received oral linerixibat 40 mg or placebo twice daily. Pruritus severity and pruritus-related sleep interference were assessed using a 0–10 numerical rating scale. The primary endpoint was change from baseline in worst itch over 24 weeks. Secondary endpoints included: at Week 2, change in worst itch; over 24 weeks, change in sleep interference; at Week 24, proportion of responders (≥ 2-, ≥ 3-, ≥ 4-point reduction in worst itch) and analysis of responses to 2 patient global impression items (itch severity and change). Safety endpoints included adverse event (AE) reporting.

Results

238 patients were randomised; 95% were female, itch severity was mean (standard deviation [SD]) 7.34 (1.54), 52% had alkaline phosphatase < 1.67 times upper limit of normal, and 47% were receiving stable therapy for pruritus. Pruritus improvement over 24 weeks was significantly greater with linerixibat than placebo: least-squares (LS) mean change -2.86 versus -2.15, adjusted mean difference -0.72; p = 0.001. At Week 24, the observed mean (SD) difference from baseline in pruritus was -3.66 (2.50) with linerixibat and -2.82 (2.32) with placebo. The effect of linerixibat was rapid and superior to placebo at Week 2: LS mean change -1.78 versus -1.07, adjusted mean difference -0.71; p < 0.001. Linerixibat also significantly improved pruritus-related sleep interference over 24 weeks versus placebo: LS mean change ‑2.77 versus -2.24, adjusted mean difference -0.53; p = 0.024. At Week 24, more patients on linerixibat than placebo achieved a ≥ 2-point (68% vs 64%), ≥ 3-point (56% vs 43%) or ≥ 4-point (41% vs 29%) reduction in pruritus and a higher proportion of linerixibat than placebo-treated patients reported their pruritus was very much improved (55% vs 37%) or absent (21% vs 9%). AEs reported more frequently with linerixibat than placebo were predominantly gastrointestinal (GI), including diarrhoea (61% vs 18% of patients) and abdominal pain (18% vs 3% of patients); 4% of patients in the linerixibat group discontinued treatment due to diarrhoea.

Conclusion

In patients with PBC and moderate-to-severe pruritus, linerixibat rapidly and significantly improved pruritus and pruritus-related sleep interference versus placebo. While GI AEs were more common with linerixibat than placebo, they rarely led to treatment discontinuation.

Disclosure

Funded by GSK. Various authors declare conflicts of interest as consultants, employee, recipients of grants and stockholders. These will be reported in full during the presentation.

Introduction

Current therapies for inflammatory bowel disease (IBD) suppress inflammation rather than inhibiting underlying microbial drivers. Treatment failures of frontline interventions, including corticosteroids, can lead to dose escalation and risk of adverse effects.^1,2 Bacteria with pro-inflammatory potential, like adherent-invasive Escherichia coli (AIEC), have been postulated as a possible microbial driver in Crohn’s disease (CD), however, targeting these bacteria with precision in IBD remains challenging.^3,4 Most antibiotics have broad-spectrum activity and disturb the background microbiome, which may exacerbate inflammation.⁵ Attention has shifted towards bacteriophages, yet their underlying mechanisms of treating IBD, and how they may work as an adjunctive therapy, remains elusive.

Aims & Methods

We aimed to assess whether and how phage therapy, specific for a CD-associated bacterium, reduces colitis severity using gnotobiotic mouse models.
In vitro kill curves and biofilm challenges were used to identify lytic phage candidates. Adult germ-free C57BL/6 mice were colonized with altered Schaedler-flora (ASF) and E. coli NRG857c (NRG), a CD-associated isolate. After 3 weeks, mice were treated with an NRG-specific lytic phage (1x10⁹ PFU/dose; daily or TIW) or vehicle (PBS) for 2 weeks (n=6/group) and then exposed to 1 cycle of dextran sulfate sodium (2%; DSS) in drinking water. PBS-treated mice (n=6) not exposed to DSS served as controls. Phage treatment was also tested in a spontaneous model of colitis using C57BL/6NTac-Il10^em8Tac (IL-10^-/-) mice, treated weekly. Mice were monitored daily for weight, stool consistency, and occult blood. Fecal contents were cultured to determine bacterial load, and the expression of NRG fimS was quantified using qPCR as an assessment of virulence. At endpoint, colon tissues were collected for histological and immunohistochemistry analysis to quantify colitis severity and NRG infiltration, respectively. Additional C57BL/6 mice were colonized and treated as previously described. During colitis induction, mice received a low-dose of budesonide (2μg/day)⁶ (n=5) or vehicle (n=5) until endpoint. Mice were monitored daily for disease activity and colon tissues were collected for histological analysis. HPLC was used to determine active budesonide levels.

Results

HER259 was identified as a lytic phage against CD-associated AIEC NRG. In ASF and NRG colonized mice, HER259 reduced clinical symptoms (p< 0.001, p< 0.001) and histological scores (p< 0.0001, p< 0.001) in chemical induced and spontaneous colitis, respectively. A 1-log reduction in NRG bacterial load was observed in HER259-treated mice (p< 0.001). Reisolated NRG exhibited a reduced FimS ON/OFF ratio (p-value < 0.01). Immunohistochemistry revealed reduced infiltration of NRG into the lamina propria following HER259 treatment, with greater accumulation in the epithelium. HER259 treatment increased the efficacy of a sub-therapeutic dosing regimen of budesonide (p< 0.001), which was independent of microbial-based drug metabolism as determined by HPLC.

Conclusion

Our results demonstrate that lytic phage targeting a CD-associated bacterium attenuates colitis in two gnotobiotic mouse models. The intervention did not lead to complete eradication of the disease-driving agent, but instead modulated bacterial virulence mechanisms and enhanced responses to corticosteroid therapy. The data suggests that alternative mechanisms should be considered when translating phage therapy to treat IBD in clinical trials.

References

1. Yan, Y. et al. Commensal bacteria promote azathioprine therapy failure in inflammatory bowel disease via decreasing 6-mercaptopurine bioavailability. Cell Rep Med 4, 101153 (2023).
2. Nagayama, M., Gogokhia, L. & Longman, R. S. Precision microbiota therapy for IBD: premise and promise. Gut Microbes 17, 2489067 (2025).
3. Darfeuille-Michaud, A. et al. High prevalence of adherent-invasive Escherichia coli associated with ileal mucosa in Crohn’s disease. Gastroenterology 127, 412–421 (2004).
4. A, D.-M. et al. Presence of adherent Escherichia coli strains in ileal mucosa of patients with Crohn’s disease. Gastroenterology 115, 1405–1413 (1998).
5. Nelson, R. L., Suda, K. J. & Evans, C. T. Antibiotic treatment for Clostridium difficile-associated diarrhoea in adults. Cochrane Database Syst Rev 3, (2017).
6. Bercik, P. et al. Chronic gastrointestinal inflammation induces anxiety-like behavior and alters central nervous system biochemistry in mice. Gastroenterology 139, (2010).