Artificial intelligence improves quality of colonoscopies, research shows: Northwestern Medicine

SYCAMORE – Artificial intelligence has helped physicians who perform colonoscopies achieve a 13% increase in the detection and removal of colorectal polyps, according to research shared by Northwestern Medicine at a Chicago-based conference in May.

Now, Medtronic GI Genius – the Food and Drug Administration-approved computer-aided detection system using artificial intelligence that has allowed physicians to more effectively screen patients for colon cancer – is going to be equipped at every endoscopy suite in Northwestern Medicine’s nine acute-care hospitals and four outpatient locations. Included are Northwestern Medicine’s Kishwaukee Hospital, McHenry hospital and Huntley hospital.

Dr. David Manuel, a gastroenterologist for Northwestern Medicine out of Sycamore, said doctors performing colonoscopies rely on white light to illuminate a patient’s innards. That light allows doctors to see through a small camera to look for polyps, and that process still will be used now that AI is on the scene.

“But there is now a processor that tries to identify abnormalities as it can using AI,” Manuel said. “It shows up basically as a box on the screen, and it’s up to the endoscopist to determine, ‘Hey, is this real or is this something that’s just a false alarm?’ ”

Because the procedure has effectively not changed, patients who receive a colonoscopy at Northwestern Medicine, in all likelihood, will not realize artificial intelligence is essentially acting as a second set of eyes, or a second opinion, for their procedure, Manuel said.

Colorectal polyp detection rates are important to gastroenterologists because it’s the best way to measure the quality of the colonoscopy exams administered to patients.

“The higher your adenoma detection rate, or your polyp rate, the higher the likelihood that you’re able to essentially prevent colon cancer,” Manuel said. “Because what we know about colon cancer is that these tumors start out as colon polyps. If we can find the polyps at an early stage [and] remove them, we can prevent colon cancer from developing down the road.

“So anything that can help us identify the polyps, that will, in turn, help us reduce the development of colon cancer.”

Over a six-month period, 21 gastroenterologists performed 4,820 colonoscopies as a part of a Northwestern Medicine study; nine of those medical professionals used the computer-aided detection software the majority of the time.

According to a news release, the gastroenterologists who used the AI software had significantly higher polyp detection and removal rates.

Our team is constantly developing new ways to be more accurate and efficient in the care we provide. It’s incredibly gratifying to know this technology will be available to patients in every Northwestern Medicine location where colonoscopies are performed.”

—  John Pandolfino, chief of gastroenterology and hepatology at Northwestern Medicine

Adenomas, the most common type of colorectal polyp, were found and removed at a higher rate by physicians using the software than those who didn’t, and previous research has shown every 1% increase in the adenoma detection rate is associated with a 3% decrease in the risk of cancer within five years of a colonoscopy, according to the release.

“This means that computer-aided colonoscopies could reduce future colon cancer diagnoses by up to 39%,” said Dr. Rajesh Keswani, the director of endoscopy for Northwestern Memorial Hospital and director of quality for the Northwestern Medicine Digestive Health Center. “The results could even be more dramatic in suburban or rural hospitals, where fewer screening colonoscopies are performed and there may be more variation in quality.”

Dr. John Pandolfino, chief of gastroenterology and hepatology at Northwestern Medicine, also leads the Center for Artificial Intelligence and Mathematics in Gastroenterology, a first-of-its-kind program that collaborates with engineers at the McCormick School of Engineering at Northwestern University to create novel medical services.

He said Northwestern Medicine’s investment in AI signifies the health care provider’s commitment to improving patient care.

“Our team is constantly developing new ways to be more accurate and efficient in the care we provide,” Pandolfino said. “It’s incredibly gratifying to know this technology will be available to patients in every Northwestern Medicine location where colonoscopies are performed.”