This AI can help eliminate colon cancer
Michael Wallace has he performed hundreds of colonoscopies during his 20 years as a gastroenterologist. He thinks it’s pretty good to know the growths or polyps that can form on the edges of the colon and turn into cancer. But it’s not always perfect. Sometimes the polyps are flat and difficult to see. At other times, doctors miss them. “We’re all human beings,” says Wallace, who works at the Mayo Clinic. After going back to the procedure that requires attention to detail once in the morning, he says “we get tired”.
Colonoscopies, if unpleasant very effective in the study of pre-cancerous polyps and in the prevention of colon cancer. But the effectiveness of the procedure is based on the skills that the doctor performs. Now, the Food and Drug Administration has approved a new tool that will help doctors know about the growth of advanced cancers while they are having a colonoscopy. Artificial intelligence System designed by Medtronic. Doctors say that along with other measures, the tool can help improve diagnoses. “Actually, we have the potential to completely eliminate colon cancer in anyone who is kidnapped,” says Wallace, who consulted with Medtronic on the project.
The Medtronic system, called the GI Genius, has seen two more points than most doctors. Medtronic and Cosmo Pharmaceuticals trained partners on the polyp recognition algorithm while examining more than 13 million videos made by Cosmo in drug testing in Europe and the U.S. To “teach” potentially differentiating risky growths, gastroenterologists labeled the images as normal or unhealthy tissue. Then, AI was studied in increasingly difficult-to-recognize polyps, starting with colonoscopies performed under optimal conditions and moving on to more challenging challenges, distinguishing a very small polyp that was briefly or hidden in the camera’s range. dark stain.
The doctor follows a system that can be added to the areas already used for colonoscopy while the doctor examines the colon, highlighting potential polyps with a green box. GI Genius was approved in Europe in October 2019 and is the first AI cleaned by the FDA to help detect color-coded polyps “It also found things I missed,” says Wallace. first validation study GI Genius. “The system is impressive.”
Mark Pochapin, a gastroenterologist at NYU Langon who was not involved in creating GI Genius, says it makes sense that AI would help recognize polyps. “There’s less diversity when you’re studying polyps,” Pochapine says. Millions of colonoscopy videos provide a wealth of data to make the algorithm comprehensive. This should protect the system from concerns bias in other health algorithms. “There are just so many varieties of polyps,” he says.
Medtronic takes GI Genius and other AI tools as the foundation of its future business, says Giovanni Di Napoli, president of Medtronic’s GI business. To do this, the company invested a lot of time and resources to obtain FDA approval for this device. “It took us almost a year to get FDA approval,” says Di Napoli. “It’s not easy.”
Medtronic sought FDA approval under what the agency calls the de novo route, which requires applicants to provide information on the safety and efficacy of new devices including clinical data. This is a longer and more involved application that other AI medical devices have avoided. Most AI and automatic learning devices on the market are marketed using the FDA’s lighter application known as the 510 (k) path. This should prove that the device is similar to other tools already in use and usually takes about six months according to Ren research published in Lancet, Of the 222 AI devices marketed in the U.S. between 2015 and 2020, 92 percent did so through 510 (s).