cleveland’s Logo

CLEVELAND, Ohio — A colonoscopy is the best way to detect cancers of the colon and rectum, and generally a doctor uses experience to recognize areas of concern and send tissue samples for testing.

However, doctors at University Hospitals are getting some assistance – from a computer designed to look at images of the colon and detect subtle changes that even a well-trained pair of human eyes might miss.

The system, called the GI Genius, is a software module that acts like the physicians’ second set of eyes. It continuously monitors and analyzes the images during a colonoscopy and highlights suspicious polyps with a visual marker in real time – alerting the physician to places where it thinks a closer look is warranted. And it finds them 99.7% of the time, according to data by Medtronic, which manufactures the module.

Data published in the journal Gastroenterology this past July showed that the technology reduced the number of missed colorectal polyps in a standard colonoscopy by as much as 50%.

“Every 1% increase in adenoma detection rate reduces the risk of interval colorectal cancer by 3%,” said Dr. Gerard Isenberg, chief medical quality officer for the UH Digestive Health Institute. “There is currently no other technology that accomplishes that rate of success.”

UH started using the AI ​​module in March at its main campus and says it is the first Ohio hospital to fully integrate the technology into its endoscopy services.

This fall, UH will receive five more modules as part of an award through the Medtronic Health Equity Assistance Program for colorectal cancer screening. Medtronic and Amazon Web Services are donating the units to facilities that provide care to medically underserved communities with either low colorectal cancer screening rates or where access to this cutting-edge technology is not currently available.

UH is one of 62 facilities in the United States receiving the donated GI Genius modules. The hospital plans to place one of the new units in each of its general endoscopy rooms, and one unit at UH Ahuja Medical Center. Eventually, UH plans on having 20 throughout its system

Colorectal cancer is the third most common and second deadliest cancer among adults in the US But when caught early, certain types of colorectal cancers can have a five-year survival rate of over 90%.

Death rates from colorectal cancer are higher in Northeast Ohio than nationally, and the rates of diagnoses among people under 50 are increasing locally as well according to statistics from the Ohio Cancer Incidence Surveillance System. In addition, African-Americans are disproportionately affected, and have a lower five-year survival rate.

The higher mortality rates in Northeast Ohio are of concern says Isenberg, and underscore the need for better screening capabilities in our area.

“This statistic is worrisome and shows why we need to start screening at age 45 in people with no risk factors as now recommended by several national organizations, and even earlier in those people with risk factors,” said Isenberg.

“This AI module directly impacts our ability to improve colon cancer screening and prevention and offers a technology that will likely reduce health care disparities in our community.”

On Monday, Geoff Martha, CEO of Medtronic, the company that developed the GI Genius module, spoke to a packed audience of Case Western Reserve biomedical engineering students and faculty about the role of AI in the future of medical technology.

“It’s creeping into everything we do,” said Martha, who discussed the company’s use of AI in spinal surgery, deep brain stimulation for treating the symptoms of Parkinson’s disease, and diabetes management. Many aspects of medicine that are reliant upon the skill and experience of the physician or surgeon can be improved by AI said Martha. “We are bringing technology to that and turning it from an art to a science,” he said.

“Getting colorectal cancer is often terrible news,” said Isenberg. “We look forward to helping our community by providing access to a tool that will help detect lesions before they become cancers and hopefully prevent more cases.”

By ll07v

Leave a Reply

Your email address will not be published.