Medtronic and MNGI Bring Artificial Intelligence to Twin Cities Colonoscopy Exams
A sedated patient lies on his side on a surgical stretcher for a colonoscopy at MNGI Digestive Health in Plymouth.
A doctor, accompanied by a nurse and an anesthetist, performs the examination. A large screen sitting a few feet away allows the doctor to see inside the patient’s body, but it’s the little green boxes – periodically appearing on the screen – that represent the new era of medical technology.
These green boxes are artificial intelligence at work. The device used is called GI Genius and is sold by Medtronic. A green box flashes to draw the doctor’s attention to polyps and potentially cancerous lesions during routine colonoscopies.
The technology is intended to detect areas of concern that a doctor may have overlooked or missed. Detecting polyps can reduce the risk of colorectal cancer.
Medtronic, operationally based in Fridley, is making a concerted advance in artificial intelligence as a medical diagnostic tool.
“Data, AI and machine learning are the opposite of artificial and dehumanizing,” Medtronic CEO Geoff Martha said in commentary provided to the Star Tribune. “They are the key to democratizing healthcare and helping to personalize care for every individual – at scale.”
The GI Genius works on a complex algorithm, drawing on a dataset of 13 million images from thousands of colonoscopies. Since the technology first gained US Food and Drug Administration approval in April 2021, the data has already been updated three times, adding more images.
Using algorithms and machine learning, AI can analyze large amounts of data and recognize patterns that might otherwise go unnoticed. At best, AI analysis can help doctors make faster and more accurate diagnoses.
“What it is for us is a pair of electronic eyes. It makes us better,” said Dr. Scott Ketover, gastroenterologist and CEO of MNGI.
GI Genius is used in a space where the needs are great. In 2020, colorectal cancer was the second deadliest type of cancer behind lung in the United States, resulting in nearly 52,000 deaths, according to the Centers for Disease Control and Prevention.
“I think it’s breakthrough technology,” laments Giovanni Di Napoli, president of Medtronic’s gastrointestinal business. Di Napoli said Medtronic wants to bring AI technology to the diagnosis of other diseases.
“This is the first step we’re taking. GI Genius is a platform. … It’s a work in progress,” Di Napoli said.
Can artificial intelligence improve your health?
“Some of the diagnoses are where we see [AI] first,” said Dr. Genevieve Melton-Meaux, professor at the University of Minnesota Medical School and lead of care analytics and innovation for M Health Fairview.
Melton-Meaux said AI can also be used in patient monitoring, medical robotics and administrative tasks related to managing patient data.
GI Genius was developed and manufactured by Italian company Cosmo Pharmaceuticals, but Medtronic’s name appears on the device as the exclusive worldwide distributor and distributor.
Earlier this year, MNGI conducted a three-month pilot trial with four GI Genius machines at its Plymouth site.
“We’ve all had the experience of doing a procedure where the device helped find something before we were sure we saw it,” Ketover said.
A key measure for colonoscopies is the adenoma detection rate (ADR), which measures the finding of polyps during an exam. During its trial, MNGI saw its ADR increase by 17%. MNGI’s Board of Directors was convinced, approving the purchase of GI Genius modules for all of its outpatient centers.
Medtronic is deploying AI in several other products, including Linq II, an implantable heart monitor, and AccuRhythm AI, which improved monitor accuracy by eliminating false alerts.
The company’s AI algorithms can also adjust insulin delivery every five minutes for diabetic patients.
Medtronic recently won a contract from the US Department of Veterans Affairs to install 115 GI Genius modules at VA medical facilities across the United States.
The FDA calls AI and machine learning medical technology “clinical decision support software.” The agency issued new guidelines in September outlining and updating its parameters on regulatory devices using technology tools.
Melton-Meaux said the new guidelines don’t make FDA approval easier or faster, but are meant to outline best practices for evaluating AI as a medical device.
AI is now attracting technology companies that were not traditionally active in the medical sector.
Apple — known for its computer, cellphones and electronic devices — received FDA approval in June for its atrial fibrillation history feature that can be used with an Apple Watch and the Health app on a device. iPhone. It analyzes heart rate data to identify irregular heart rhythms.
Melton-Meaux said the use of AI in medical settings will continue to grow.
“I think we’re really on the precipice. We’re just at the start,” Melton-Meaux said.