P0637 - A Ubiquitous and Interoperable Deep Learning Model for Automatic Detection of Pleomorphic Gastroesophageal Lesions

Francisco Mendes, MD¹, Miguel Mascarenhas Saraiva, MD, PhD¹, Miguel Martins, MD¹, Maria João Almeida, MD¹, João Afonso, MD¹, Joana Frias, MD¹, Catarina Araujo, MD¹, Tiago Ribeiro, MD¹, Pedro Cardoso, MD¹, Joana Mota, MD¹, Patrícia Andrade, MD¹, Hélder Cardoso, MD¹, Miguel Mascarenhas Saraiva, MD, PhD², João Ferreira, PhD³, Guilherme Macedo, MD, PhD¹
1Centro Hospitalar Universitário São João, Porto, Porto, Portugal; 2ManopH Gastroenterology Clinic, Porto, Porto, Portugal; 3Faculdade de Engenharia da Universidade do Porto, Porto, Porto, Portugal

Introduction: Artificial intelligence (AI) has been widely explored recently to enhance capsule endoscopy (CE), with the goal of improving the reading process efficiency. The majority of AI models focus on analyzing the small intestine and colon, while the development of esophagogastric (E-G) models has been limited by the lack of frames, posing a challenge to building models with robust performance. This study aims to develop an interoperable ubiquitous model capable detecting pleomorphic lesions in the E-G tract.

Methods: A total of 59,482 endoscopic frames were included from 774 CE procedures conducted across 5 medical centers to train a Convolutional Neural Network (CNN). The data were separated following an exam-based split, with 90% assigned to training set - including a 5-fold cross-validation —and the remaining 10% reserved for testing. The main performance metrics evaluated included sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC).

Results: In training set, the average sensitivity was 85.0% (95% confidence interval: 76.5–93.5), specificity was 96.3% (95% CI: 93.9–98.7) and accuracy was 93.6% (95% CI: 91.7–95.4), with an area under the ROC curve (AUC-ROC) of 0.98 (95% CI: 0.97–0.98). In the testing phase, the sensitivity was 92.2%, specificity was 95.1%, and accuracy was 94.6%.

Discussion: AI models for CE that can evaluate the esophagus and stomach represent an important advancement toward creating a comprehensive panendoscopic system. This ubiquitous and interoperable model has shown robust accuracy in identifying lesions in both regions. Nonetheless, further prospective studies in real-world clinical settings are essential to confirm its effectiveness compared to conventional upper endoscopy.


Figure: Figure 1 - Study Design and Results of an Ubiquitous artificial intelligence model for detection of pleomorphic esophago-gastric lesions in capsule endoscopy

Disclosures:
Francisco Mendes indicated no relevant financial relationships.
Miguel Mascarenhas Saraiva indicated no relevant financial relationships.
Miguel Martins indicated no relevant financial relationships.
Maria João Almeida indicated no relevant financial relationships.
João Afonso indicated no relevant financial relationships.
Joana Frias indicated no relevant financial relationships.
Catarina Araujo indicated no relevant financial relationships.
Tiago Ribeiro indicated no relevant financial relationships.
Pedro Cardoso indicated no relevant financial relationships.
Joana Mota indicated no relevant financial relationships.
Patrícia Andrade indicated no relevant financial relationships.
Hélder Cardoso indicated no relevant financial relationships.
Miguel Mascarenhas Saraiva indicated no relevant financial relationships.
João Ferreira indicated no relevant financial relationships.
Guilherme Macedo indicated no relevant financial relationships.

Francisco Mendes, MD¹, Miguel Mascarenhas Saraiva, MD, PhD¹, Miguel Martins, MD¹, Maria João Almeida, MD¹, João Afonso, MD¹, Joana Frias, MD¹, Catarina Araujo, MD¹, Tiago Ribeiro, MD¹, Pedro Cardoso, MD¹, Joana Mota, MD¹, Patrícia Andrade, MD¹, Hélder Cardoso, MD¹, Miguel Mascarenhas Saraiva, MD, PhD², João Ferreira, PhD³, Guilherme Macedo, MD, PhD¹. P0637 - A Ubiquitous and Interoperable Deep Learning Model for Automatic Detection of Pleomorphic Gastroesophageal Lesions, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.