Video/Image Library of Endoscopy Procedures for the Development of AI-empowered Endoscopy Quality Reporting and Educational Modules

For EGD procedures, the following data will be documented: the exact time to reach the GE junction, the diaphragmatic hiatus, body/fondus/antrum of stomach, duodenum, procedural time during EGD, complications (immediate and late: first 24h post-procedure and 14 days post-procedure, respectively), the use of a distal attachment cap, insufflation and desufflation, cardiac retroflexion for facilitating visualization of mucosa during EGD, the use of existing AI platforms that increase lesion detection (CADe) and classification (CADx), the AI classification (autonomous CADx diagnosis), the endoscopists' ODs without CADx, the endoscopists' ODs after seeing the diagnosis from CADx (CADx-assisted diagnosis), the performance of endoscopists (measured with detection rates such as ADR, AADR, SSLDR, PDR, or with detection counts such as APC).

For colonoscopy procedures, the following data will be documented: the exact time to reach the caecum, caecum intubation, the exact time of the visualisation of each anatomical landmarks, confirmed time of each lesion, ulcer, polyp visualised by the endoscopist, withdrawal time, mucosal inspection time, and complications (immediate and late: 24h post-procedure and 14 days post-procedure, respectively), the use of existing AI platforms that increase lesion detection (CADe) and classification (CADx), the AI classification (autonomous CADx diagnosis), the endoscopists' ODs without CADx, the endoscopists' ODs after seeing the diagnosis from CADx (CADx-assisted diagnosis), the performance of endoscopists (measured with detection rates such as ADR, AADR, SSLDR, PDR, or with detection counts such as APC). In the case of patients with rectal cancer, any active disease, such as tumor recurrence will be documented.

For upper and lower endoscopies, polyp, lesion, or ulcer-related characteristics will be documented: anatomical location, size estimated by the endoscopists, surface and vascular pattern and morphology. Any other pathological findings with the description of severity and anatomical location will be documented. Any biopsies taken during the procedure, and their location will be documented, including the number and a description of the biopsied tissue, as well as the reason for the biopsy.

In case of IBD indication, Crohn's disease and ulcerative colitis endoscopic characteristics will be graded and documented. The inflammation, ulceration/erosion, stricture, bleeding, and their related severity or extent in each colon segment will be documented. The endoscopic characteristics of the colon will also be documented, using components of the Mayo Score / DAI for Ulcerative Colitis, including vessels and bleeding.

In case of hiatal hernia, the size of the hernia along with the related type will be documented.

In case of esophagitis (GERD), the Los Angeles classification of esophagitis will be used to define the grade and extent of the inflammation. The MUSE classification system will also be used to categorise esophageal lesions and strictures.

In case of Barrett's esophagus, a detailed description of the esophagus will be documented: presence and extent of Barrett's esophagus, including the length of Barrett's segment in cm, the classification of Barrett's esophagus, the presence or absence of hiatal hernia and its size, and any sign of reflux esophagitis alongside their severity and location. The Prague classification will be used to describe the circumferential and maximal Barrett's segment length. The number and locations of biopsies taken within the Barrett's segment, at the GE junction, and in any suspicious area. The size and characteristics of any polyps or nodules found within the Barrett's segment will be documented as biopsies are essential for grading dysplasia and monitoring disease progression.