Polyp REcognition Assisted by a Device Interactive Characterization Tool - The PREDICT Study — PREDICT  

Artificial Intelligence Clinical Trial

Official title: Polyp REcognition Assisted by a Device Interactive Characterization Tool - The PREDICT Study

Status Completed

Clinical Trial Summary

Diminutive colorectal polyps (≤ 5 mm) represent most of the polyps detected during colonoscopy, especially in the rectum-sigmoid tract. The characterization of these polyps by virtual chromoendoscopy is recognized as a key element for innovative imaging techniques. As a matter of facts diminutive colorectal polyps are very frequent and, if located in the rectosigmoid colon, they present a very low malignant risk (0.3% of evolution towards advanced adenoma and up to 0.08% of evolution towards invasive carcinoma). The real-time characterization would allow to identify the lowest risk polyps (hyperplastic subtype), to leave them in situ or, if resected, not to send them for histological examination, allowing a huge saving in healthcare associated costs.

Recently, the American Society for Gastrointestinal Endoscopy (ASGE) Technology Committee established the Preservation and Incorporation of Valuable endoscopic Innovations (PIVI) document, specific for real-time histological assessment for tiny colorectal polyps, to establish reference quality thresholds. Two performance standards have been developed to guide the use of advanced imaging:

1. for diminutive polyps to be resected and discarded without pathologic assessment, endoscopic technology (when used with high confidence) used to determine histology of polyps ≤ 5mm in size, when combined with the histopathology assessment of polyps > 5 mm in size, should provide a ≥ 90% agreement in assignment of post-polypectomy surveillance intervals when compared to decisions based on pathology assessment of all identified polyps;

2. in order for a technology to be used to guide the decision to leave suspected rectosigmoid hyperplastic polyps ≤ 5 mm in size in place (without resection), the technology should provide ≥ 90% negative predictive value (when used with high confidence) for adenomatous histology.

Computer-Aided-Diagnosis (CAD) is an artificial intelligence-based tool that would allow rapid and objective characterization of these lesions. The GI Genius CADx was developed to help endoscopists in their clinical practices for polyps characterization.

Clinical Trial Description

n/a

Related Conditions & MeSH terms

• Artificial Intelligence

• NCT number: NCT04589078
• Study type: Observational
• Source: Cosmo Pharmaceuticals NV
• Status: Completed
• Start date: September 8, 2020
• Completion date: December 22, 2020