The Impact of Colon Cancer
According to the National Institutes of Health (NIH), colon cancer is the third-leading type of cancer death in the United States. Cancer in the colon usually starts from polyps or other precancerous growths in the rectum or the colon (large intestine). As part of a colorectal cancer screening and surveillance plan, colonoscopies are performed to detect changes or abnormalities in the lining of the colon and rectum. A colonoscopy involves threading an endoscope (thin, flexible tube with a camera at the end) through the rectum and throughout the entire length of the colon, allowing a doctor to see signs of cancer or precancerous lesions.
ML Hardware and AI Software To Aid Doctors
The U.S. Food and Drug Administration (FDA) granted marketing authorization of the GI Genius to Cosmo Artificial Intelligence, Ltd. GI Genius is the first device that uses artificial intelligence (AI) based on machine learning (ML) to assist in the detection of lesions, such as polyps or suspected tumors, in the colon in real time during a colonoscopy.
This guide analyzes how artificial intelligence – including machine learning – can be used by pharmaceutical and medical device companies to improve the clinical data review and cleansing process.
As explained by Dr. Courtney Lias, Director of the FDA’s Center for Devices and Radiological Health, “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. 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, clinicians now have a tool that could help improve their ability to detect gastrointestinal lesions they may have missed otherwise.”
What Is GI Genius?
The GI Genius is comprised of integrated hardware and software that 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.” 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 to the doctor that further assessment may be needed. Options include:
- a closer visual inspection
- tissue sampling
- testing or removal
- or burning the lesion with a laser
The GI Genius does not (at least yet anyway) characterize or classify a lesion. The system does not provide any diagnostic assessments of colorectal polyp pathology, nor does it suggest to the doctor how to manage suspicious polyps. GI Genius only identifies regions of the colon within the endoscope’s field of view where a colorectal polyp might be located, allowing for a more extended examination in real time during colonoscopy. It is up to the doctor to decide whether the identified region actually contains a suspected lesion, and how the lesion should be managed and processed per standard clinical practice and guidelines.
Safety and Detection Impact of GI Genius
The FDA assessed the safety and effectiveness of the GI Genius through a multi-center, prospective, randomized, controlled study in Italy with 700 subjects. Subjects were 40-80 years old who were undergoing a colonoscopy for colorectal cancer screening. The primary analyses from the study were based on a sub-population of 263 patients who were being screened or surveilled every three years or more. Study subjects underwent either white light standard colonoscopy with the GI Genius (136 patients) or standard white light colonoscopy without the GI Genius (127 patients).
The primary endpoint of the study compared how often colonoscopy plus GI Genius identified a patient with at least one lab-confirmed tumor, either cancerous or precancerous, to the frequency the standard colonoscopy made the same identifications. In the study, colonoscopy plus GI Genius was able to identify lab-confirmed tumors in 55.1% of patients compared to identifying them in 42.0% of patients with standard colonoscopy.
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.