Centro Hospitalar Universitário São João Porto, Porto, Portugal
Miguel Martins, MD1, Miguel Mascarenhas Saraiva, MD, PhD1, João Ferreira, PhD2, João Afonso, MD1, William Sonnier, MD3, Bruno Rosa, MD4, Tiago Ribeiro, MD1, Tiago Cúrdia Gonçalves, MD4, Francisco Mendes, MD1, Pedro Campelo, MD4, Claúdia Macedo, MD4, Pedro Cardoso, MD1, Joana Mota, MD1, Maria João Almeida, MD5, António Miguel M P D. Martins Pinto da Costa, MD6, Ana Perez-Gonzalez, MD7, Jorge Mendoza, MD8, Thiciane Cavalcante, MD9, Erika Fortes, MD10, Matheus Ferreira de Carvalho, MD11, Marcos Eduardo Lera dos Santos, MD11, Artur Kaffes, MD12, Robert Feller, MD13, Benjamin Niland, MD14, Patrícia Andrade, MD5, Hélder Cardoso, MD1, Eduardo Hourneaux De Moura, MD, PhD15, Cecilio Santander, MD, PhD16, Jack Di Palma, MD, MACG17, Jose Cotter, MD, PhD4, Guilherme Macedo, MD, PhD1 1Centro Hospitalar Universitário São João, Porto, Porto, Portugal; 2Faculdade de Engenharia da Universidade do Porto, Porto, Porto, Portugal; 3University of South Alabama College of Medicine, Mobile, AL; 4Hospital da Senhora da Oliveira, Guimarães, Braga, Portugal; 5Centro Hospitalar Universitário de São João, Porto, Porto, Portugal; 6Hospital Universitario Puerta de Hierro-Majadahonda, Madrid, Madrid, Spain; 7Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Madrid, Spain; 8Hospital Universitario La Princesa, Pamplona, Navarra, Spain; 9Hospital Sírio-Libanês, São Paulo, Sao Paulo, Brazil; 10Albert Einstein Israelite Hospital, São Paulo, Sao Paulo, Brazil; 11Hospital das Clínicas da Faculdade de Medicina da Universidade de Sao Paulo, São Paulo, Sao Paulo, Brazil; 12Royal Prince Alfred Hospital, Sydney, New South Wales, Australia; 13St. Vincent's Hospital, Sydney, New South Wales, Australia; 14University of South Alabama, Alabama, AL; 15Hospital das Clínicas da Faculdade de Medicina da USP, São Paulo, Sao Paulo, Brazil; 16Department of Gastroenterology, Hospital Universitario La Princesa, Madrid, Madrid, Spain; 17USA Health, University of South Alabama, Mobile, AL Introduction: Capsule endoscopy (CE) plays a central role in evaluating small bowel pathology, particularly in patients with iron-deficiency anemia or obscure gastrointestinal (GI) bleeding. Vascular lesions—such as angiectasias and red spots—are among the most frequent findings in CE and a leading cause of bleeding in these settings. Accurate identification of these lesions is crucial for diagnosis and therapeutic planning. However, CE interpretation remains time-consuming and prone to reader variability. Artificial intelligence (AI), especially convolutional neural networks (CNNs), offers a promising solution to enhance lesion detection, improve consistency, and reduce interpretation time. This study aimed to develop and validate an AI model for detecting and classifying vascular lesions across multiple CE platforms and clinical environments. Methods: A prospective, multicenter study was conducted from January 2021 to April 2025, involving nine centers across Portugal, Spain, Brazil, Australia, and the USA. A total of 398 anonymized CE exams were analyzed, acquired using three different systems (PillCam SB2, SB3, and Olympus EC-10). Each video underwent standard-of-care (SoC) reading, followed by an AI-assisted interpretation. Discrepancies were adjudicated by an independent expert panel to establish the gold standard. Diagnostic performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Results: Vascular lesions were confirmed in 234 patients (58.9%) by expert consensus. AI-assisted reading achieved higher sensitivity (94.4% vs. 64.5%) and overall accuracy (83.8% vs. 71.6%) than SoC. Specificity was slightly lower with AI (68.3% vs. 82.0%). The AI model’s superiority over SoC was statistically significant (p < 0.001). Average reading time was reduced to 316 seconds per video using AI assistance. Discussion: This large multicenter study shows that AI-assisted CE significantly improves detection of vascular lesions with substantial time savings. The use of multiple CE systems and international clinical sites supports the model’s robustness, interoperability, and real-world applicability. These results reinforce AI’s role in enhancing CE-based diagnosis of GI bleeding and anemia-related conditions.
Figure: Main findings
Disclosures: Miguel Martins indicated no relevant financial relationships. Miguel Mascarenhas Saraiva indicated no relevant financial relationships. João Ferreira indicated no relevant financial relationships. João Afonso indicated no relevant financial relationships. William Sonnier: Abbvie – Speakers Bureau. Eli Lily – Speakers Bureau. Bruno Rosa indicated no relevant financial relationships. Tiago Ribeiro indicated no relevant financial relationships. Tiago Cúrdia Gonçalves indicated no relevant financial relationships. Francisco Mendes indicated no relevant financial relationships. Pedro Campelo indicated no relevant financial relationships. Claúdia 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 Perez-Gonzalez indicated no relevant financial relationships. Jorge Mendoza indicated no relevant financial relationships. Thiciane Cavalcante indicated no relevant financial relationships. Erika 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. Artur Kaffes indicated no relevant financial relationships. Robert Feller indicated no relevant financial relationships. Benjamin Niland indicated no relevant financial relationships. Patrícia Andrade indicated no relevant financial relationships. Hélder 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. Jose Cotter indicated no relevant financial relationships. Guilherme Macedo indicated no relevant financial relationships.
Miguel Martins, MD1, Miguel Mascarenhas Saraiva, MD, PhD1, João Ferreira, PhD2, João Afonso, MD1, William Sonnier, MD3, Bruno Rosa, MD4, Tiago Ribeiro, MD1, Tiago Cúrdia Gonçalves, MD4, Francisco Mendes, MD1, Pedro Campelo, MD4, Claúdia Macedo, MD4, Pedro Cardoso, MD1, Joana Mota, MD1, Maria João Almeida, MD5, António Miguel M P D. Martins Pinto da Costa, MD6, Ana Perez-Gonzalez, MD7, Jorge Mendoza, MD8, Thiciane Cavalcante, MD9, Erika Fortes, MD10, Matheus Ferreira de Carvalho, MD11, Marcos Eduardo Lera dos Santos, MD11, Artur Kaffes, MD12, Robert Feller, MD13, Benjamin Niland, MD14, Patrícia Andrade, MD5, Hélder Cardoso, MD1, Eduardo Hourneaux De Moura, MD, PhD15, Cecilio Santander, MD, PhD16, Jack Di Palma, MD, MACG17, Jose Cotter, MD, PhD4, Guilherme Macedo, MD, PhD1. P0934 - Multicenter Validation of an AI Tool for Detecting Small Bowel Vascular Lesions in Capsule Endoscopy, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.
