Role of AI in CE for the Identification of SB Lesions in Patients With Small Intestinal Bleeding.

NCT04821349 | Completed

• 1 other identifier: ArtiC STUDY-NP4350 v.05 140920
• Study Type: interventional
• Target: 137
• Locations: 1 country
• Sites: 1

Brief Summary

Capsule Endoscopy (CE) is a safe, patient friendly and easy procedure performed for the evaluation of gastrointestinal tract unable to be explored via conventional endoscopy. The most common indication to perform SBCE is represented by Suspected Small Bowel Bleeding (SSBB). According to the widest meta-analysis available in literature, SBCE shows a diagnostic yield in SSBB of about 60%, and angiodysplasias are the most relevant findings, accounting for 50% of patients undergoing SBCE for SSBB. Accordingly, it represents the first line examination in SSBB investigation for determining the source of bleeding, if primary endoscopy results negative. Despite its high clinical feasibility, the evaluation of CE-video-captures is one of the main drawbacks since it is time consuming and requests the reader to concentrate to not miss any lesion. In order to reduce reading time, several software have been developed with the aim to cut similar images and select relevant images. For example, automated fast reading software have demonstrated to significantly reduce reading time without impacting the miss rate in pathological conditions affecting diffusely the mucosa (as IBD lesions do). Not the same assumption can be taken for isolated lesions since several studies reported an unacceptable miss rate for such a detection modality. New advancements such as artificial intelligence made their appearance in recent years. Deep convolutional neural networks (CNNs) have demonstrated to recognize specific images among a large variety up to exceed human performance in visual tasks. A Deep Learning model has been recently validated in the field of Small Bowel CE by Ding et al. According to their data collected on 5000 patients, the CNN-based auxiliary model identify abnormalities with 99.88% sensitivity in the per patient analysis and 99.90% sensitivity in the per-lesion analysis. With this perspective, it is believable that AI applied to SBCE can significantly shorten the reading time and support physicians to detect available lesions without losing significant lesions, further improving the diagnostic yield of the procedure.

Conditions

Iron Deficiency Anemia; Obscure Gastrointestinal Bleeding

Outcome Measures

Primary Outcomes (1)

• Accuracy of AI-assisted video reading versus traditional video reading with conventional software.

  sensitivity, specificity, PPV, NPV calculated at per-patient analysis for P1 / P2 lesions, compared with the adjudication committee as gold standard in case of discrepancies.

  through study completion, an average of 1 year

Secondary Outcomes (6)

• evaluation of Reading time of AI-assisted reading compared with conventional reading

  through study completion, an average of 1 year

• Role of AI-assisted reading in real life from a health economic perspective

  through study completion, an average of 1 year

• Accuracy of AI-assisted video reading versus traditional video reading with conventional software.

  through study completion, an average of 1 year

• Accuracy of AI-assisted video reading versus traditional video reading with conventional software considering any lesions for a per-patient analysis with the adjudication committee as gold standard in case of discrepancies.

  through study completion, an average of 1 year

• Diagnostic yield of CE

  through study completion, an average of 1 year

Study Arms (1)

Single arm study

OTHER

Standard reading Group vs AI-assisted reading Group

Device: Capsule endoscopy

Interventions

Capsule endoscopy DEVICE

A consecutive series of patients recruited by 12 European centers based on the indication of OGIB will undergo capsule endoscopy examination. Capsule endoscopy will be performed in each site according to local rules and requirements, and the study protocol will concern only the post-procedure analysis on reading modalities for each patient.

Single arm study

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• indication of OGIB:1)after negative upper and lower endoscopy; 2)France: after negative pregnancy test; 3)Hb cut-off male: \<13, female: \<12

You may not qualify if:

• Age \< 18 years old
• Known or suspected intestinal obstruction
• Non-steroidal anti-inflammatory drugs (twice weekly or more) during the 4 weeks preceding enrollment
• Patient is expected to undergo MRI examination within 7 days after ingestion of the capsule
• Patient with known gastrointestinal motility disorders
• Subjects with known or suspected delayed gastric emptying
• Patient suffers from any condition, such as swallowing problems, which precludes compliance with study and/or device instructions
• Patient has any allergy or other known contraindication or intolerance to the medications used in the study
• Patient has any condition, which precludes compliance with study and/or device instructions
• Patient with any contraindication to take the bowel preparation product
• Women who are either pregnant or nursing at the time of screening, or are of child- bearing potential and do not practice medically acceptable methods of contraception
• Concurrent participation in another clinical trial using any investigational drug or device
• Patient suffers from a life-threatening condition
• Patients with history or clinical evidence of renal disease and/or previous clinically significant laboratory abnormalities of renal function parameters
• Patients with pace-maker or implantable cardioverter

Sponsors & Collaborators

• Fondazione Poliambulanza Istituto Ospedaliero: lead
• Humanitas Hospital, Italy: collaborator
• Fondazione Policlinico Universitario Agostino Gemelli IRCCS: collaborator
• Skane University Hospital: collaborator
• Hospital Clinic of Barcelona: collaborator
• Universitätsklinikum Hamburg-Eppendorf: collaborator
• Sheffield Teaching Hospitals NHS Foundation Trust: collaborator
• Endo-Kapszula Magánorvosi Centrum: collaborator
• Szeged University: collaborator
• Saint Antoine University Hospital: collaborator
• Hospital Avicenne: collaborator
• South Tyneside and Sunderland NHS Foundation Trust: collaborator
• Northwick Park Hospital: collaborator
• Hospices Civils de Lyon: collaborator
• Royal Free Hospital NHS Foundation Trust: collaborator
• Union Hospital, Tongji Medical College, Huazhong University of Science and Technology: collaborator

Study Sites (1)

Fondazione Poliambulanza

Brescia, 25124, Italy

Location

Related Publications (1)

• Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, Keuchel M, McAlindon M, Finta A, Rosztoczy A, Dray X, Salvi D, Riccioni ME, Benamouzig R, Chattree A, Humphries A, Saurin JC, Despott EJ, Murino A, Johansson GW, Giordano A, Baltes P, Sidhu R, Szalai M, Helle K, Nemeth A, Nowak T, Lin R, Costamagna G. AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. Lancet Digit Health. 2024 May;6(5):e345-e353. doi: 10.1016/S2589-7500(24)00048-7.

  PMID: 38670743 DERIVED

MeSH Terms

Conditions

Anemia, Iron-Deficiency

Interventions

Capsule Endoscopy

Condition Hierarchy (Ancestors)

Anemia, Hypochromic; Anemia; Hematologic Diseases; Hemic and Lymphatic Diseases; Iron Deficiencies; Iron Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases

Intervention Hierarchy (Ancestors)

Endoscopy, Gastrointestinal; Endoscopy, Digestive System; Endoscopy; Diagnostic Techniques, Surgical; Diagnostic Techniques and Procedures; Diagnosis

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Masking Details: Each center will receive from another center anonymized patient videos that have been uploaded on an encrypted USB key. Indeed, expert gastroenterologists from each center will proceed with AI-assisted video reading without knowing which center the video comes from nor the results of the normal reading. Reading conditions are the same as for standard reading. Results from both normal and AI-assisted reading will be compared. In the case of significant disagreement between the results from conventional capsule endoscopy reading and AI-assisted reading (e.g. missed lesions), a consensus review for each center will be done. Any lesion shall be considered.
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 12, 2021
• First Posted: March 29, 2021
• Study Start: February 16, 2021
• Primary Completion: May 5, 2022
• Study Completion: October 1, 2022
• Last Updated: February 21, 2024

Record last verified: 2022-11

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL

Locations

IT (1)