US approval for first AI device to help detect colon cancer

The US Food and Drug Administration (FDA) has authorised a new medical device that uses artificial intelligence (AI) based on machine learning to help clinicians detect potentials signs of colon cancer.

The GI Genius device consists of hardware and software designed to highlight portions of the colon where the device detects a potential lesion.

The software uses AI algorithm techniques to identify regions of interests – during a colonoscopy, the device system generates markers and superimposes them on the video from the endoscope camera when it identifies a potential lesion.

Clinicians can then use these signals to further assess certain areas, by performing a closer visual inspection, tissue sampling, testing or removal or ablation of the lesion.

The FDA assessed the GI Genius device through a study in Italy with 700 subjects aged 40-80 years old who were undergoing a colonoscopy for colorectal cancer screening, surveillance, positive results from a previous faecal immunochemical test for blood in the stool or gastrointestinal symptoms for positive colorectal cancer.

The primary endpoint of the study compared how often colonoscopy plus the GI Genius device identified a patient with at least one lab-confirmed precancerous tumour or cancer tumour to how often standard colonoscopy made the same identifications.

In the study, colonoscopy plus GI Genius was able to identify lab-confirmed tumours in 55.1% of patients compared to identifying them in 42.0% in patients with standard colonoscopy.

Colorectal cancer is the third leading cause of death from cancer in the US, according to the US National Institutes of Health.

The GI Genius device was reviewed by the FDA through its De Novo premarket review pathway, which is used 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.