Introduction

Capsule endoscopy (CE) is frequently employed as the first exam when mid-gastrointestinal bleeding is suspected, following normal upper and lower endoscopies. While its primary focus is on evaluating the small bowel, detection of vascular lesions both upstream and downstream could also hold clinical importance.

Aims & Methods

The aim of this study is to develop and test a Convolutional Neural Network (CNN)-based model for panendoscopic automatic detection of vascular lesions during CE. A retrospective study involving 2 centers was conducted, involving 1188 CE exams. A total of 152,312 frames were utilized, obtained from seven distinct types of CE devices, with 14,942 frames being classified as vascular lesions (angiectasias or varices) after triple validation. The data was divided in training/validation (90%) and test (10%) sets, using an exam-split design. A 5-fold cross-validation was conducted during training/validation set. The all process was iterated five times. The primary outcome measures were sensitivity, specificity, accuracy, area under the conventional receiver operating characteristic curve (AUC-ROC) and the precision-recall curve (AUC-PR), from the training/validation set.

Results

The model demonstrated a mean sensitivity and specificity of 87.5% (IC95% 81.5 – 93.6%) and 99.5% (IC95% 99.3 – 99.7%), respectively. Mean accuracy was 98.4% (IC95% 97.7 – 99.1%). Mean AUC-ROC value was 0.987 (IC95% 0.980 – 0.995), while AUC-PR value was 0.998 (IC95% 0.997 – 1.000).

Conclusion

This represents the first proof-of concept AI deep learning model developed for panendoscopic automatic detection of vascular lesions during CE. The CCN’s high diagnostic performance in multibrand devices addresses a critical issue of technological interoperability, allowing it to be replicated in multiple technological settings.

Introduction

Guselkumab (GUS), a dual-acting interleukin-23p19 subunit inhibitor, demonstrated efficacy in participants (pts) with ulcerative colitis (UC) treated with intravenous (IV) or subcutaneous (SC) induction. Here, we report the efficacy and safety of SC induction followed by SC maintenance through Week (W) 48 in ASTRO, a phase 3, randomized, double-blind, placebo (PBO)-controlled, treat-through study in pts with moderately to severely active UC.

Aims & Methods

Eligible pts had modified Mayo scores of 5 to 9, rectal bleeding subscore of ≥1, and Mayo endoscopic subscore (MES) ≥2. Pts also had documented inadequate response/intolerance to biologics, Janus kinase (JAK) inhibitors, and/or sphingosine-1-phosphate (S1P) inhibitors (BIO/JAKi/S1Pi-IR) or to corticosteroids, 6-mercaptopurine, or azathioprine. Randomization was stratified by baseline BIO/JAKi/S1Pi-IR status and MES with 418 pts allocated 1:1:1 to GUS 400 mg SC every 4 weeks (q4w) (×3)→GUS 200 mg SC q4w (N=140), GUS 400 mg SC q4w (×3)→GUS 100 mg SC every 8 weeks (q8w) (N=139), or PBO SC (N=139). PBO pts who met rescue criteria were switched to GUS at W16; GUS pts who met rescue criteria stayed on their assigned GUS dose regimen (sham rescue).

Results

At W48, greater proportions of pts in the GUS groups achieved clinical remission compared with PBO (36.7% for GUS 100 mg q8w [Δ 29.5%], 42.9% for GUS 200 mg q4w [Δ 35.6%], 7.2% for PBO) (Table). Endoscopic remission proportions were 25.9% for GUS 100 mg q8w (Δ 20.9%), 26.4% for GUS 200 mg q4w (Δ 21.4%), and 5.0% for PBO. Clinical response, symptomatic remission, endoscopic improvement, histologic improvement, and histologic remission proportions were also greater for GUS vs PBO. Consistent with the results of the overall population, efficacy was also observed for subpopulations of BIO/JAKi/S1Pi-naïve and BIO/JAKi/S1Pi-IR pts. Safety events per 100 pts-years were not greater in the GUS groups compared with the PBO group: adverse events (AE) (GUS 100 mg q8w and 200 mg q4w vs PBO: 308.3 and 310.7 vs 357.1), serious AEs (6.5 and 8.2 vs 38.4), serious infections (0.8 and 2.5 vs 3.7), and AEs leading to treatment discontinuation (4.9 and 4.1 vs 19.8).
Table. Efficacy endpoints at Week 48 in the overall population and by biologic, JAK inhibitor, and/or S1P inhibitor history

Conclusion

GUS SC induction followed by SC maintenance was efficacious through 1 year in pts with moderately to severely active UC, and the safety profile is consistent with GUS in its approved indications including UC.

Disclosure

ML reports research support from Lilly, Pfizer, and Takeda; consulting for AbbVie, Bristol Myers Squibb, Intercept, Janssen (Johnson & Johnson), Lilly, Pfizer, Prometheus, Roivant, Takeda, and Target RWE.
JRA reports grant support from Janssen, Merck, and Pfizer; consultancy fees from AbbVie, Adiso, Bristol Myers Squibb, Ferring, Genentech, GlaxoSmithKline, Janssen, Merck, Pfizer, Roivant, Celltrion, TrexBio, Shattuck Labs and Seres Therapeutics; payments for speaking from AbbVie, Bristol Myers Squibb, and Janssen; and is a steering committee member and investigator for Janssen.
SD reports consultancy fees from AbbVie, Alimentiv, Allergan, Amgen, AstraZeneca, Athos, Biogen, Boehringer Ingelheim, Celgene, Celltrion, Eli Lilly, Enthera, Ferring, Gilead, Hospira, Inotrem, Janssen, Johnson & Johnson, MSD, Mundipharma, Mylan, Pfizer, Roche, Sandoz, Sublimity, Takeda, TiGenix, UCB, and Vifor; and reports lecture fees from AbbVie, Amgen, Ferring, Gilead, Janssen, Mylan, Pfizer, and Takeda.
MG, TB, YA, KH, SJ, LJ, and HZ are employees of and may own stock in Johnson & Johnson.
TH reports research grants from AbbVie GK, Boston Scientific Corporation, EA Pharma Co. Ltd., JIMRO Co. Ltd., Kissei Pharmaceutical Co. Ltd., Kyorin Pharmaceutical Co. Ltd., Mitsubishi Tanabe Pharma Corporation, Mochida Pharmaceutical Co. Ltd., Nippon Kayaku Co. Ltd., Pfizer Inc., Takeda Pharmaceutical Co. Ltd., and Zeria Pharmaceutical Co. Ltd.; consulting fees from AbbVie GK, Abivax, Bristol Myers Squibb, EA Pharma Co. Ltd., Gilead Sciences, Janssen Pharmaceutical K.K., Lilly, Mitsubishi Tanabe Pharma Corporation, and Pfizer Inc.; and lecture fees from AbbVie GK, EA Pharma Co. Ltd., Janssen Pharmaceutical K.K., JIMRO Co., Kissei Pharmaceutical Co. Ltd., Kyorin Pharmaceutical Co. Ltd., Mitsubishi Tanabe Pharma Corporation, Mochida Pharmaceutical Co., Ltd., Pfizer Inc., and Takeda Pharmaceutical Co. Ltd.
DTR reports consulting and/or speaker fees and/or advisory board participation for AbbVie, Altrubio, Apex, Avalo, Bristol Myers Squibb, Buhlmann Diagnostics, Celgene, Connect BioPharma, Intouch Group, Iterative Health, Janssen (Johnson & Johnson), Lilly, Pfizer, Samsung Neurologica, and Takeda; Altrubio, Datos Health, and Iterative Health stock options; grants from Takeda; and membership on the Board of Directors of Cornerstones Health, Inc. and on the Crohn’s & Colitis Foundation’s Board of Trustees.
LPB reports grants or contracts from Celltrion, Fresenius Kabi, Medac, MSD, and Takeda; consulting and/or payment or honoraria and/or data safety monitoring board or advisory board participation for AbbVie, Abivax, Adacyte, Alfasigma, Alimentiv, Amgen, Applied Molecular Transport, Arena, Banook, Biogen, Bristol Myers Squibb, Celltrion, Connect Biopharm, Cytoki Pharma, Enthera, Ferring, Fresenius Kabi, Galapagos, Genentech, Gilead, Gossamer Bio, GlaxoSmithKline, IAC Image Analysis, Index Pharmaceuticals, Inotrem, Janssen, Kern Pharma, Lilly, Medac, Mopac, Morphic, MSD, Nordic Pharma, Novartis, Oncodesign Precision Medicine, ONO Pharma, OSE Immunotherapeutics, Pandion Therapeutics, Par' Immune, Pfizer, Prometheus, Protagonist, Roche, Samsung, Sandoz, Sanofi, Satisfay, Takeda, Telavant, Theravance, Thermo Fischer, Tigenix, Tillots, Viatris, Vectivbio, Ventyx, and Ysopia; and meeting attendance/travel support from AbbVie, Alfasigma, Amgen, Celltrion, Connect Biopharm, Ferring, Galapagos, Genentech, Gilead, Gossamer Bio, Janssen, Lilly, Medac, Morphic, MSD, Pfizer, Sandoz, Takeda, Thermo Fischer, and Tillots.

Introduction

Microscopic colitis (MC) refers to two pathologies – Collagenous colitis (CC) and Lymphocytic colitis (LC) that cause chronic watery diarrhoea, urgency, incontinence leading to significantly decreased quality of life¹. It is thought that MC develops due to a pathological immune response to intestinal luminal antigens in genetically predisposed individuals, with microbiota playing an important role^{2, 3}. However, the pathogenesis of MC is still unclear.

Aims & Methods

The aim of this study was to identify and characterize changes in bacterial composition of MC patients in terminal ileum and different colonic segments and determine its relation to the clinical course of disease. Biopsies from terminal ileum and six segments of the colon were collected during diagnostic colonoscopies. DNA extraction was performed using AllPrep DNA/RNA Micro Kit (Qiagen) following the manufacturer’s instructions. To determine bacterial composition, sequencing of the 16S rRNA variable region V3-V4 was conducted using the 27F and 338R polymerase chain reaction primers and sequenced on a MiSeq (2×250 bp; Illumina, Hayward, CA). Bioinformatic analysis was performed using DADA2, and taxonomic classification was carried out with the RDP classifier.

Results

Biopsy samples from 20 active CC patients, 20 active LC patients, and 50 controls demonstrated distinct microbial profiles across different intestinal segments, as revealed by beta-diversity and differential compositional analyses. Compared with controls, CC patients had consistent alterations in three bacterial families throughout the entire colon, with Erysipelatoclostridiaceae and Coriobacteriaceae decreased and Pasteurellaceae increased. Additionally, 35 families had segment-specific changes, and 25 families displayed altered abundance in the terminal ileum.
LC patients exhibited a consistent increase in Erisypelotrichaceae across the entire colon, with 38 other families showing segmental changes, and 12 families displaying altered abundance in the terminal ileum. Comparing LC and CC revealed a significantly different bacterial profile. LC showed lower abundance across many families, particularly in the right colon and terminal ileum. After sample collection, 15 CC patients and 12 LC patients received budesonide, with 3 CC and 2 LC patients having incomplete response. Beta diversity analysis revealed significant differences in the ascending colon and left side of the colon of CC patients based on response to budesonide. Patients with incomplete response to budesonide had an increased abundance of the genus Paucibacter. Similar tendencies were not observed in LC.
1 CC patient exhibited a quiescent disease course, 6 reached a sustained remission after treatment, 7 had a relapsing and 6 had a chronic active disease. Significant differences in beta diversity were observed in transverse, descending colon and rectum. Beta diversity of the descending colon had a medium correlation with disease behaviour. In the LC group 6 patients had a quiescent disease, 8 had a sustained remission after treatment, 3 exhibited a relapsing and 4 had a chronic active disease. No significant correlation between microbiota and disease behaviour was observed in LC.

Conclusion

This study showed significant differences in bacterial composition between CC, LC and controls in the terminal ileum and colon. In both CC and LC, bacterial alterations were not consistent throughout the entire colon but varied between different colonic segments. Microbiome differences based on response to budesonide and disease behaviour were observed in CC, but not LC.

References

1. Verhaegh BPM, Münch A, Guagnozzi D, et al. Course of Disease in Patients with Microscopic Colitis: A European Prospective Incident Cohort Study. J Crohns Colitis. 2021;15(7):1174-1183.
2. Miehlke S, Guagnozzi D, Zabana Y, et al. European guidelines on microscopic colitis: United European Gastroenterology (UEG) and European Microscopic Colitis Group (EMCG) statements and recommendations. United European Gastroenterol J. Published online 2020.
3. Burke KE, D’Amato M, Ng SC, Pardi DS, Ludvigsson JF, Khalili H. Microscopic colitis. Nat Rev Dis Primers. 2021;7(1).

Introduction

Between 50% and 70% of patients with Crohn’s disease (CD) will require an ileocecal resection. Surgery is not curative, and endoscopic recurrence is frequently observed at the anastomosis site and/or in the neo-terminal ileum.
The objective of this study was to analyse the mucosa-associated ileal microbiota at the time of surgery and during the colonoscopy performed 6 months later and to identify predictive factors of post-operative endoscopic recurrence.

Aims & Methods

Patients were recruited from 15 centres within the REMIND group. Since September 2010, the REMIND group has established a homogeneous, prospective, multicenter cohort (POP-REMIND, NCT03458195) of patients undergoing surgery for ileal and/or ileocolonic Crohn’s disease. Samples were collected from the surgical specimen and during endoscopy, centrally stored in a biobank, and analysed to identify factors associated with recurrence.
Inclusion criteria were: age ≥18 years, ileal or ileocecal CD requiring intestinal resection. Data were collected using an electronic case report form (eCRF). Post-operative treatment was prescribed according to a predefined algorithm. Clinical, therapeutic, biological, and endoscopic data (Rutgeerts classification) were collected 6 months after surgery.
The composition of the mucosa-associated ileal microbiota was analysed at the time of surgery in 140 patients (M0) and in 125 samples at the colonoscopy performed 6 months later (M6), using ultra-deep 16S and ITS2 sequencing (MiSeq, Illumina) to characterize bacterial and fungal microbiota.
We specifically selected patients who had not received antibiotics during the perioperative period to avoid biasing the analysed signal. Sequencing data were processed using the DADA2 pipeline. Alpha and beta diversity and microbiota composition were analysed. Bacterial taxa associated with clinical parameters were identified using MaAsLin2 (Multivariate Association with Linear Models), accounting for CD phenotype and treatments.

Results

We observed numerous differences in the ileal bacterial and fungal microbiota between M0 and M6, and between patients who experienced recurrence (>i2a) and those who were in remission at M6. At M6, the Rutgeerts score was the main factor associated with variability in microbiota composition. The abundance of certain species, notably a decrease of Faecalibacterium prausnitzii, or increase of Fusobacterium nucleatum and Akkermansia muciniphila, was differentially associated with a whole range of levels of the Rutgeerts score or with more specific scores characterizing the inflammation of the anastomosis or the ileum. In addition, machine learning approaches displayed better performances when considering the Rutgeerts score as a multilevel prediction instead of a binary classification, further confirming the need to consider its full range. Finally, we investigated the microbial community dynamics, which highlighted a denser network organisation after surgery and in the absence of recurrence, along with changes in keystone species.

Conclusion

The ileal microbiota associated with post-operative recurrence in CD follows a dynamic process characterized by several waves of alterations. The link between ileal microbiota and disease recurrence varies depending on whether the lesions are located at the anastomosis or ileum sites, supporting a different underlying pathogenesis for the inflammatory process at these two locations.