FDA Clears First AI Device to Find Possible Cancerous Hot Spots During Colonoscopies

April 10, 2021
AJMC Staff

The device, which highlights for gastroenterologists regions of the colon that have visual characteristics consistent with possible cancerous abnormalities, is already in use in Europe.

The FDA Friday authorized the marketing of an artificial intelligence (AI) device based on machine learning to assist clinicians in detecting polyps or suspected tumors during a colonoscopy.

According to the National Institutes of Health, colorectal cancer is the third leading cause of death from cancer in the United States.

The GI Genius is designed to highlight portions of the colon where the device detects a potential lesion. The software uses artificial intelligence algorithm techniques to identify regions of interest. The GI Genius is designed to be compatible with many FDA-cleared standard video endoscopy systems.

During a colonoscopy, the GI Genius system generates markers, which look like green squares and are accompanied by a short, low-volume sound, and superimposes them on the video from the endoscope camera when it identifies a potential lesion.

These signs signal that further assessment may be needed, such as a closer visual inspection, tissue sampling, testing or removal, or ablation of the lesion.

The FDA assessed the safety and effectiveness of the GI Genius through a multicenter, prospective, randomized, controlled study in Italy with 700 subjects aged 40 to 80 who were undergoing a colonoscopy.

The primary analyses were based on a sub-population of 263 patients who were being screened or surveilled every 3 years or more. Study subjects underwent either white light standard colonoscopy with the GI Genius (136 patients) or standard white light colonoscopy alone (127 patients).

The primary endpoint compared how often colonoscopy plus GI Genius identified a patient with at least one lab-confirmed adenoma (precancerous tumor) or carcinoma to how often standard colonoscopy made the same identifications.

Colonoscopy plus GI Genius was able to identify lab-confirmed adenomas or carcinomas in 55.1% of patients, compared with identifying them in 42.0% of patients with standard colonoscopy, an observed difference of 13%.

There were no adverse events reported with the additional biopsies, but there was a slight increase in the number of lesions biopsied that were not adenomas.

The FDA reviewed the GI Genius through the De Novo premarket review pathway, a regulatory pathway for some low- to moderate-risk devices that are novel and for which there is no legally marketed predicate device to which the device can claim substantial equivalence.

In a statement, the FDA said its Center for Devices and Radiological Health’s Digital Health Center of Excellenceis looking to the future of AI-based technology, including in its Artificial Intelligence and Machine Learning (AI/ML)-Based Software as a Medical Device Action Plan.

“Artificial intelligence has the potential to transform health care to better assist health care providers and improve patient care. When AI is combined with traditional screenings or surveillance methods, it could help find problems early on, when they may be easier to treat,” Courtney H. Lias, PhD, acting director of the GastroRenal, ObGyn, General Hospital and Urology Devices Office in the FDA’s Center for Devices and Radiological Health, said in a statement. “Studies show that during colorectal cancer screenings, missed lesions can be a problem even for well-trained clinicians. With the FDA’s authorization of this device today, clinicians now have a tool that could help improve their ability to detect gastrointestinal lesions they may have missed otherwise.”

The GI Genius is not intended to characterize or classify a lesion, nor to replace lab sampling as a means of diagnosis. The FDA granted marketing authorization of the GI Genius to its developer, Cosmo Artificial Intelligence; the device will be sold by Medtronic.