Preventing Colorectal Cancer With AI Technology

Advances Help Enhance Colonoscopy Screenings

Published April 2022

Gastroenterologists from the Northwestern Medicine Digestive Health Center are using the latest artificial intelligence (AI) technology during colonoscopies to help them prevent colorectal cancer. The team is measuring how new software can help physicians find precancerous colorectal polyps and improve colonoscopy screenings.

"We are constantly developing and implementing new ways to improve the quality of screening colonoscopies to provide our patients with world-class care," says Rajesh N. Keswani, MD, director of Quality and director of Endoscopy for the Digestive Health Center. "The thorough screening colonoscopies we provide to patients can take time as we carefully look for colorectal cancer. Artificial intelligence supports our efforts by using robust data to help physicians identify polyps or lesions in their earliest stages."

The system is just the latest effort to use AI to enhance patient care in the Digestive Health Center, says John E. Pandolfino, MD, chief of Gastroenterology and Hepatology at Northwestern Medicine, who also leads the Center for Artificial Intelligence and Mathematics in Gastroenterology. The center is the first of its kind, developed in collaboration with engineers at Northwestern University McCormick School of Engineering.

When a gastroenterologist uses the AI software during a colonoscopy, a green box appears on screen and highlights areas that the technology has identified as potentially precancerous. The physician then examines the tissue to decide if it needs to be removed for further analysis.

We are constantly developing new ways to improve the quality of colonoscopies.

— Rajesh Keswani, MD

"Artificial intelligence and machine learning have the potential to vastly improve our ability to accurately predict, diagnose and treat our patients living with digestive diseases," says Dr. Pandolfino.

The Center for Artificial Intelligence and Mathematics focuses on three main initiatives:

Developing virtual organs, which can be used to study the effects of surgery and medications
Developing new hybrid diagnostic tools that use AI and machine learning to enhance diagnoses
Using machine learning and neural networks to predict disease outcomes

After Dr. Keswani and his colleagues finish assessing the new AI software, they will share their findings with Gastroenterology colleagues across Northwestern Medicine to consider rolling it out to other Northwestern Medicine hospitals.

"It is always our goal to make the latest technologies accessible to all of the communities served by our health system," says Dr. Pandolfino. "Our close collaboration with our suburban and rural colleagues leads to better care for every patient."