P4072 - Multicenter Real-World Validation of an AI-Based System for Detecting Protruding Lesions in Capsule Endoscopy

Miguel Mascarenhas Saraiva, MD, PhD¹, João Afonso, MD¹, João Ferreira, PhD², Francisco Mendes, MD¹, William Preston Sonnier, ³, Bruno Rosa, ⁴, Tiago Ribeiro, MD¹, Tiago Cúrdia Gonçalves, ⁵, Miguel Martins, MD⁶, Pedro Campelo, ⁷, Claudia Macedo, ⁷, Pedro Cardoso, MD¹, Joana Mota, MD¹, Maria João Almeida, MD⁶, António Miguel M P D. Martins Pinto da Costa, MD⁸, Ana Pérez González, MD⁹, Jorge Mendoza, ¹⁰, Thicianie Andrade Cavalcante, ¹¹, Erika Borges Fortes, ¹², Matheus Ferreira de Carvalho, MD¹³, Marcos Eduardo Lera dos Santos, MD¹³, Arthur kaffes, ¹⁴, Robert Feller, ¹⁵, Ana Patricia Andrade, ¹⁶, Helder Cardoso, ¹⁶, Eduardo Hourneaux De Moura, MD, PhD¹⁷, Cecilio Santander, ¹⁰, Jack Di Palma, MD, MACG¹⁸, José Cotter, ⁵, Guilherme Macedo, MD, PhD¹
1Centro Hospitalar Universitário São João, Porto, Porto, Portugal; 2Faculdade de Engenharia da Universidade do Porto, Porto, Porto, Portugal; 3Department of Gastroenterology, University of South Alabama, Mobile, AL; 4Department of Gastroenterology, Hospital da Senhora da Oliveira, Guimarães, Braga, Portugal; 5Hospital da Senhora da Oliveira, Guimarães, Braga, Portugal; 6Centro Hospitalar Universitário de São João, Porto, Porto, Portugal; 7Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Braga, Portugal; 8Hospital Universitario Puerta de Hierro-Majadahonda, Madrid, Madrid, Spain; 9Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Madrid, Spain; 10Hospital Universitario La Princesa, Madrid, Madrid, Spain; 11Hospital Sírio-Libanês Brasília, Brasília, Distrito Federal, Brazil; 12Hospital Israelita Albert Einstein, São Paulo, Sao Paulo, Brazil; 13Hospital das Clínicas da Faculdade de Medicina da Universidade de Sao Paulo, São Paulo, Sao Paulo, Brazil; 14Royal Prince Alfred Hospital, Camperdown, New South Wales, Australia; 15St Vincent's Public and Private Hospitals, Melbourne, Victoria, Australia; 16Precision Medicine Unit, São João University Hospital, Porto, Porto, Portugal; 17Hospital das Clínicas da Faculdade de Medicina da USP, São Paulo, Sao Paulo, Brazil; 18USA Health, University of South Alabama, Mobile, AL

Introduction: Capsule endoscopy (CE) is a non-invasive imaging method widely used for small bowel evaluation. Among its findings, protruding lesions are relatively common but challenging to detect due to the time-consuming nature of CE review and susceptibility to human oversight. Artificial intelligence (AI) tools, particularly convolutional neural networks (CNNs), may improve diagnostic performance. However, robust real-world data validating their effectiveness remain limited. This study aimed to evaluate the diagnostic accuracy of an AI system for detecting small bowel protruding lesions in full-length CE videos across diverse clinical environments.

Methods: In a prospective, multicenter study, 398 CE videos from nine centers across Portugal, Spain, Brazil, Australia, and the United States were analyzed. The dataset included videos from three different CE systems. All exams underwent conventional reading followed by an AI-assisted interpretation using a CNN trained to detect protruding lesions. An independent expert adjudicated discrepancies between the two readings, establishing the reference standard. Performance was assessed using sensitivity, specificity, and overall accuracy. Mean reading time per video was also recorded.

Results: The AI system identified 107 confirmed protruding lesions, compared to 47 detected via standard reading. Sensitivity with AI was significantly higher (92.8% vs. 46.3%), while specificity was moderately lower (79.8% vs. 93.5%). The AI model’s superiority[1] over conventional interpretation was statistically significant (p < 0.001). Additionally, AI-assisted reading reduced the average interpretation time to 316 seconds per video.

Discussion: This multicenter study demonstrates that AI-assisted capsule endoscopy substantially enhances detection of protruding lesions, nearly doubling sensitivity compared to conventional reading, with an acceptable trade-off in specificity. The inclusion of data from multiple CE platforms and international centers supports the generalizability and interoperability of the model. These findings highlight the potential of AI to streamline CE workflows and improve diagnostic accuracy in routine clinical practice.


Figure: Study design flowchart


Figure: Automatic detection of protruding lesion.

Disclosures:
Miguel Mascarenhas Saraiva indicated no relevant financial relationships.
João Afonso indicated no relevant financial relationships.
João Ferreira indicated no relevant financial relationships.
Francisco Mendes indicated no relevant financial relationships.
William Preston Sonnier indicated no relevant financial relationships.
Bruno Rosa indicated no relevant financial relationships.
Tiago Ribeiro indicated no relevant financial relationships.
Tiago Cúrdia Gonçalves indicated no relevant financial relationships.
Miguel Martins indicated no relevant financial relationships.
Pedro Campelo indicated no relevant financial relationships.
Claudia Macedo indicated no relevant financial relationships.
Pedro Cardoso indicated no relevant financial relationships.
Joana Mota indicated no relevant financial relationships.
Maria João Almeida indicated no relevant financial relationships.
António Miguel Martins Pinto da Costa indicated no relevant financial relationships.
Ana Pérez González indicated no relevant financial relationships.
Jorge Mendoza indicated no relevant financial relationships.
Thicianie Andrade Cavalcante indicated no relevant financial relationships.
Erika Borges Fortes indicated no relevant financial relationships.
Matheus Ferreira de Carvalho indicated no relevant financial relationships.
Marcos Eduardo Lera dos Santos indicated no relevant financial relationships.
Arthur kaffes indicated no relevant financial relationships.
Robert Feller indicated no relevant financial relationships.
Ana Patricia Andrade indicated no relevant financial relationships.
Helder Cardoso indicated no relevant financial relationships.
Eduardo Hourneaux De Moura indicated no relevant financial relationships.
Cecilio Santander indicated no relevant financial relationships.
Jack Di Palma indicated no relevant financial relationships.
José Cotter indicated no relevant financial relationships.
Guilherme Macedo indicated no relevant financial relationships.

Miguel Mascarenhas Saraiva, MD, PhD¹, João Afonso, MD¹, João Ferreira, PhD², Francisco Mendes, MD¹, William Preston Sonnier, ³, Bruno Rosa, ⁴, Tiago Ribeiro, MD¹, Tiago Cúrdia Gonçalves, ⁵, Miguel Martins, MD⁶, Pedro Campelo, ⁷, Claudia Macedo, ⁷, Pedro Cardoso, MD¹, Joana Mota, MD¹, Maria João Almeida, MD⁶, António Miguel M P D. Martins Pinto da Costa, MD⁸, Ana Pérez González, MD⁹, Jorge Mendoza, ¹⁰, Thicianie Andrade Cavalcante, ¹¹, Erika Borges Fortes, ¹², Matheus Ferreira de Carvalho, MD¹³, Marcos Eduardo Lera dos Santos, MD¹³, Arthur kaffes, ¹⁴, Robert Feller, ¹⁵, Ana Patricia Andrade, ¹⁶, Helder Cardoso, ¹⁶, Eduardo Hourneaux De Moura, MD, PhD¹⁷, Cecilio Santander, ¹⁰, Jack Di Palma, MD, MACG¹⁸, José Cotter, ⁵, Guilherme Macedo, MD, PhD¹. P4072 - Multicenter Real-World Validation of an AI-Based System for Detecting Protruding Lesions in Capsule Endoscopy, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.