This study aims to validate and evaluate AI algorithms for detection and characterization of early GI neoplasia.
Male or Female, aged 18 years or above.
Requiring gastroscopy and/or colonoscopy to investigate gastrointestinal symptoms, or as part of screening or ongoing surveillance of GI neoplasia.
Participant is willing and able to give informed consent for participation in the study.
Patients with endoscopically active severe oesophagitis
Poor bowel preparation
In phase (1), all previously collected, anonymized and stored endoscopic images and videos of early GI neoplasia in the departmental endoscopy teaching and training library. In phase (2), all eligible patients coming for upper and/or lower GI endoscopy for clinical reasons in participating centres will be approached for enrolment into this study.
Other
Prospective
collection of endoscopic images and videos
Other interventioncollection of endoscopic images and videos
neoplasia detection rate
neoplasia detection rate of the AI algorithms in different locations of the GI tract.
Accuracy of AI diagnosis
Accuracy of real time optical diagnosis (characterization) of GI neoplasia by the AI algorithm.
Endoscopist neoplasia detection rate
Detection rate of endoscopists at various levels of experience
Click on the lead sponsor to view all of their trials.
