FDA Approves AI Tool to Help Detect Colon Cancer

By Jonathan Springston, Editor, Relias Media

The FDA has approved an artificial intelligence (AI) tool to help clinicians detect lesions, polyps, and tumors during routine colon screening.

During a colonoscopy, the GI Genius uses an algorithm to identify regions, generating colored markers and sounds when it detects a possible trouble spot in the organ. Based on these electronic cues, the clinician could inspect closer, take tissue samples in the area for additional testing, or remove the concerning sign.

“When AI is combined with traditional screenings or surveillance methods, it could help find problems early on, when they may be easier to treat,” Courtney H. Lias, PhD, acting director of the GastroRenal, ObGyn, General Hospital, and Urology Devices Office in the FDA’s Center for Devices and Radiological Health, said in a statement. “Studies show that during colorectal cancer screenings, missed lesions can be a problem even for well-trained clinicians. With the FDA’s authorization … clinicians now have a tool that could help improve their ability to detect gastrointestinal lesions they may have missed otherwise.”

The agency based its approval on an Italian study that included 700 patients age 40 to 80 years who either underwent a standard colonoscopy or a standard colonoscopy supplemented with assistance from the GI Genius device. Researchers observed colonoscopy plus GI Genius helped clinicians identify lab-confirmed adenomas or carcinomas in 55.1% of patients vs. identifying them in 42% of patients with standard colonoscopy. Using GI Genius led to more biopsies, but there were no reported adverse events. Still, the FDA stressed this AI device is not meant to replace traditional screening and testing methods, but rather to serve as another tool in the armamentarium.

The healthcare industry is finding many creative uses for AI. Covenant Medical Center in Saginaw, MI, recently used AI-driven technology to protect staff and improve the quality of care for patients in its emergency care unit, completely automating the medication reconciliation process. Patient access leaders are encouraging registrars to embrace AI to make self-service easier and to improve the patient experience.

In the ED, AI is considered a promising tool to improve stroke diagnosis. During the COVID-19 pandemic, EDs used new approaches to help manage COVID-19-related capacity challenges without adversely affecting patient care. Researchers developed an automated text messaging approach that can monitor patients who have been discharged from the ED. Other investigators have leveraged AI to train an algorithm to help emergency clinicians better predict outcomes and manage resources.