FDA Authorizes Marketing of First AI Diagnostic Device for Colon Cancer

The FDA has authorized the marking of GI Genius, the first device that uses artificial intelligence (AI) to assist in the diagnosis of colon cancer, according to a press release by the FDA.

GI Genius is meant to be used during a colonoscopy to assist clinicians in detecting lesions such as suspected tumors or polyps in real time. The device highlights portions of the colon where a potential lesion is detected. It then uses AI to identify areas of interest and generate markers. The device then signals to health care provides that further assessment may be needed, such as a tissue sample, testing, closer visual inspection, removal or ablation of the lesions. It is compatible with many standard, FDA approved video endoscopy systems.

The safety and effectiveness of the GI Genius devices was assessed in a randomized, multicenter study (NCT04441580) involving 700 participants between the ages of 40-80 years old who were undergoing a colonoscopy for colorectal cancer screening, surveillance, or positive results from a previous fecal immunochemical test for blood in the stool or gastrointestinal symptoms of possible colorectal cancer.

Patients were split into 1 of 2 arms, the experimental arm or the active comparator arm. During the experimental arm, patients underwent a colonoscopy with AI while those in the active comparator arm just underwent a standard colonoscopy. Primary outcomes included rate of advanced adenomas and the rate of patients detected with 3 or more adenomas. Secondary outcomes included overall adenoma and polyp detection rate, size of lesions detected, rate of neoplasia by colonic site, post-colonoscopy surveillance, time of cecal intubation, among others.

In order to participate, patients must have been undergoing a colonoscopy. Patients unable or unwilling to give informed consent or those reporting the use of anti-platelet agents were not eligible to participate.

At an interim analysis of 263 patients who were being screened or surveilled every 3 years or more, 136 underwent colonoscopy with the GI Genius and 127 underwent a standard white light colonoscopy alone. Lab-confirmed adenomas or carcinomas were found in 55.1% of patients who underwent colonoscopy with GI Genius compared to the 42% of patients who underwent standard colonoscopy.

No adverse events were reported with the additional biopsies, such as perforations, bleeding, or infections. There was, however, a slight increase in biopsied lesions that were not adenomas.

“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,” said Courtney H. Lias, PhD, acting director of the GastroRenal, OB/GYN, general hospital and urology devices office in the FDA’s Center for Devices and Radiological Health in a press release. “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.”

GI Genius is not intended to classify or characterize a lesion, nor replace lab sampling. Additionally, it does not provide any diagnostic assessments of colorectal polyp pathology nor does it suggest how to manage suspicious polyps. It only identifies regions within the endoscope’s field of view. 

_REFERENCE:

_{FDA authorizes marketing of first device that uses artificial intelligence to help detect potential signs of colon cancer. News release. FDA. April 9, 2021. Accessed April 14, 2021. https://bit.ly/3uQLopz.}