EP331 - A Novel Deep Learning Model for Predicting Colorectal Anastomotic Dehiscence: A Pioneer Multicenter Transatlantic Study

ePoster Presenter(s)

• MM

  Miguel Mascarenhas, n/a

  Gastroenterology, Centro Hospitalar Universitario de Sao Joao
  Hospital São João, Porto.
  Porto, Porto, Portugal

  All disclosed relationships have been reviewed and managed prior to the start of this activity. Any relevant relationships will be listed below. This individual has no financial relationships to disclose

  View ePoster

Author(s)

• AC

  António Costa, MD

  Department of Gastroenterology, Puerta del Hierro University Hospital
  .
  ., Madrid, Spain

  Disclosure information not submitted.
• MC

  Matheus Carvalho, MD

  Dr
  Hospital das Clinicas da Faculdade de Medicina da Universidade de São Paulo de Ribeirão Preto
  São Paulo, Sao Paulo, Brazil

  Disclosure information not submitted.
• FM

  Francisco Mendes, .

  Department of Gastroenterology, São João University Hospital
  .
  ., Porto, Portugal

  Disclosure information not submitted.
• AS

  André Santos, MD

  Dr
  Faculdade de Medicina da Universidade do Porto
  Porto, Porto, Portugal

  Disclosure information not submitted.
• FF

  Filipa Fonseca, MD

  Dr
  Instituto Português de Oncologia IPO, Lisboa, Portugal,
  Lisboa, Lisboa, Portugal

  Disclosure information not submitted.
• EC

  Eduardo Carvalho, n/a

  Mr
  Institute of Science and Innovation in Mechanical and Industrial Engineering
  Porto, Porto, Portugal

  Disclosure information not submitted.
• GB

  Guilherme Barbosa, MD

  Dr
  INEGI – Institute of Science and Innovation in Mechanical and Industrial Engineering, Porto, Portugal,
  Porto, Porto, Portugal

  Disclosure information not submitted.
• NR

  Nilza Ramião, n/a

  Ms
  Institute of Science and Innovation in Mechanical and Industrial Engineering
  Porto, Porto, Portugal

  Disclosure information not submitted.
• MV

  Maisa Vasconcellos, MD

  Dr
  Hospital das Clínicas da Faculdade de Medicina de USP - Ribeirão Preto, São Paulo, Brazil
  Ribeirão Preto, Sao Paulo, Brazil

  Disclosure information not submitted.
• AB

  Abdullah Bunaiyan, n/a

  Dr
  Royal Liverpool University Hospital, Liverpool
  liverpool, England, United Kingdom

  Disclosure information not submitted.
• MJ

  Maria João Almeida, n/a

  Department of Gastroenterology, São João University Hospital
  .
  ., Porto, Portugal

  Disclosure information not submitted.
• JM

  Joana Mota, n/a

  Dr
  Hospital São João, Porto.
  Porto, Porto, Portugal

  Disclosure information not submitted.
• TR

  Tiago Ribeiro, n/a

  Department of Surgery, Instituto de Infectologia Emílio Ribas
  .
  ., Porto, Portugal

  Disclosure information not submitted.
• MM

  Miguel Martins, n/a

  Engineer
  Faculty of Engineering of the University of Porto
  Porto, Porto, Portugal

  Disclosure information not submitted.
• PC

  Pedro Cardoso, MD

  Dr
  Centro Hospitalar Universitário de São João, Gastroenterology, Porto, Portugal
  Porto, Porto, Portugal

  Disclosure information not submitted.
• AP

  Antonio Pinto da Costa, .

  Department of Gastroenterology, Puerta del Hierro University Hospital
  .
  ., Porto, Portugal

  Disclosure information not submitted.
• ML

  Marcos Lera dos Santos, n/a

  Dr
  Hospital das Clinicas da Faculdade de Medicina da Universidade de São Paulo de Ribeirão Preto
  São Paulo, Sao Paulo, Brazil

  Disclosure information not submitted.
• EM

  Eduardo Guimarães Moura, PhD

  Dr
  Hospital São Luiz Rede D'or
  São Paulo, Sao Paulo, Brazil

  Disclosure information not submitted.
• MF

  Marley Feitosa, MD

  Dr
  Hospital das Clínicas da Faculdade de Medicina de USP - Ribeirão Preto, São Paulo, Brazil
  Ribeirão Preto, Sao Paulo, Brazil

  Disclosure information not submitted.
• JA

  Javed Ashamed, .

  Department of Surgery, NHS Royal Liverpool University Hospital
  .
  Liverpool, England, United Kingdom

  Disclosure information not submitted.
• GM

  Guilherme Macedo, .

  Department of Gastroenterology, São João University Hospital
  .
  ., Porto, Portugal

  Disclosure information not submitted.

Senior Author(s)

• ML

  Manuel Limbert, MD, PhD

  Dr
  Instituto Português de Oncologia IPO, Lisboa, Portugal
  Lisboa, Lisboa, Portugal

  Disclosure information not submitted.

Purpose/Background: Colorectal anastomotic dehiscence (CAD) is one of the most severe postoperative complications in colorectal surgery, significantly

impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no realtime

predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative recording of the

anastomosis for CAD prediction.

Methods/Interventions: A convolutional neural network (CNN) was trained using a dataset of annotated frames from colorectal surgery

videos across three international high-volume centers: IPO Lisboa, Hospital das Clínicas de Ribeirão Preto, São Paulo, Brazil and Royal

Liverpool University Hospital. The dataset included a total of 5,356 annotated frames from 26 patients, 2,007 frames classified as

CAD-positive and 3,349 as CAD-negative. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were

tested. Performance was evaluated using sensitivity, specificity, accuracy, and area under the receiver operating characteristic

(AUROC) curve. Heatmaps were generated to identify key regions influencing predictions.

Results/Outcomes: The best-performing model achieved an accuracy of 99.55%, AUROC of 99.60%, sensitivity of 99.21%, specificity of 100%,

PPV of 100%, and NPV of 98.94%. The model reliably identified CAD-positive frames and provided visual explanations through

heatmaps.

Conclusion/Discussion: To our knowledge, this is the first AI model developed to predict CAD using intraoperative video analysis. Its accuracy

suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger

dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAD before it occurs, marking a

paradigm shift in colorectal surgery.

Heatmap generated by the deep learning model identifying the region of the image responsible for the anastomosis leakage prediction
Performance metrics on the testing dataset set. PPV - positive predictive value. NPV - negative predictive value. AUROC - area under the receiver operating characteristic curve.