Author(s): Justin Williams, Nova Szoka, MD, FACS, FASMBS
Medtronic received FDA approval for the GI Genius in April 2021.
The GI Genius is an artificial intelligence system used to aid in the detection of polyps and other precancerous lesions during routine colorectal screening. During screening colonoscopies, the GI Genius generates on-screen markers as well as short, low volume sounds to signal to clinicians that a suspected lesion has been detected and requires closer inspection and investigation.
The GI Genius consists of both hardware and software components that are compatible with many FDA-cleared white-light endoscopy devices. This allows endoscopists to incorporate artificial intelligence into their procedures with minimal effort.
The safety and efficacy of the GI Genius was assessed by the FDA through a multicenter, prospective, randomized, and controlled study in Italy. In this study, white-light endoscopy with the assistance of GI Genius, was able to identify lab-confirmed adenomas and carcinomas in 55.1% of patients, compared to 42.0% in the white-light endoscopy control group, with an observed difference of 13%. Use of the GI Genius led to an increased number of biopsies performed, but no adverse events were reported as a result.
The FDA determined that the GI Genius is effective in assisting endoscopists in identifying possible lesions, allowing the clinician to further investigate the potential lesion. The GI Genius should not be used as a replacement for clinical decision-making, as further investigation is required by the endoscopist.
Indications for use:
- Adult patients undergoing screening and surveillance endoscopic mucosal evaluations
Contraindications:
- Patients who do not meet the criteria to undergo standard white-light endoscopy
References:
Hassan C, Wallace MB, Sharma P, Maselli R, Craviotto V, Spadaccini M, Repici A. New artificial intelligence system: first validation study versus experienced endoscopists for colorectal polyp detection. Gut. 2020 April;69(5):799-800. http://dx.doi.org/10.1136/gutjnl-2019-319914.