Endocytoscopic identification of dysplasia in the Barrett’s esophagus using artificial intelligence as a second assessor: a prospective assessment of the interaction between gastroenterologists and a convolutional neural network
Completed
- Conditions
- Barrett's esophagus, (low/high grade) dysplasia, esophageal adenocarcinoma
- Registration Number
- NL-OMON27377
- Lead Sponsor
- niversity Medical Center Groningen (UMCG)
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Completed
- Sex
- Not specified
- Target Recruitment
- 52
Inclusion Criteria
oPatients with established BE scheduled for gastroscopy due to surveillance examination;
oPatients with established BE and a malignant visible lesion scheduled for gastroscopy due to endoscopic mucosal resection (EMR) or Endoscopic Submucosal Dissection (ESD).
oAge = 18 years;
oWritten informed consent.
Exclusion Criteria
oAge younger than 18 years
oInability to give written informed consent for the study
Study & Design
- Study Type
- Observational non invasive
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Diagnostic accuracy is defined as sensitivity, specificity, predictive value and likelihood ratio’s. Measures: true positives, true negatives, false positives and false negatives of endocytoscopy procedure. Gold standard for comparison is the histopathological result of biopsy which will be extracted from reports of patients’ digital medical chart for which they will have to provide consent.
- Secondary Outcome Measures
Name Time Method <br>Kappa values for inter-observer agreement. <br>Procedural qualities will consist of the rating of image quality and additional procedural time for making endocytoscopic images. <br>Basic demographic data: gender, year of birth.