Chippewa Valley Times

University of Wisconsin-Eau Claire (UWEC) students Brayden Mau and Alex Rolli are collaborating with Dr. Rahul Gomes, associate professor of computer science, and Mayo Clinic Health System professionals to develop an AI model aimed at improving patient care by summarizing and extracting key information from colonoscopy reports.

“These are patient diagnoses we are talking about,” says Mau, a third-year UWEC student from Kimberly. “It’s real human lives we’re talking about.”

The project began in February 2024 following an idea from Dr. Sushil Garg, a gastroenterologist at Mayo Clinic Health System in Eau Claire, who sought ways to alleviate the increasing workloads of physicians. Dr. Rajeev Chaudhry, director of AI and bioinformatics at Mayo Clinic Health System, supported the initiative, recognizing its importance.

Blugolds Mau and Rolli utilized machine learning knowledge distillation techniques to create a condensed colonoscopy report highlighting essential parameters such as the number of polyps discovered. This streamlined document aims to reduce the time required for physicians to extract vital diagnostic information.

Currently, the researchers are validating the model's accuracy before developing a user interface intended for use by both physicians and patients.

“I was surprised at how they could follow instructions and execute them because the concepts of deep learning and large language models are pretty new,” Gomes says of his students' progress. “They were pretty quick at figuring out how things can be done.”

Sarah Harper, operations manager for the Mayo Clinic Health System AI and biomedical informatics team, commended the students’ efforts: “It’s been great for these physicians who have these innovative ideas but didn’t have access to that engineering expertise until Alex and Brayden came along to take their idea and translate it into reality.”

Gomes emphasized that this research provides students with a comprehensive experience involving mentorship from UWEC faculty on deep learning and guidance from Mayo Clinic software engineers on integrating and optimizing systems safely.

Mau noted that this hands-on research experience has allowed him to apply classroom knowledge to real-world healthcare challenges: “I’ve learned how to create all these different things in class... It’s not really something you can teach in class.”

Dr. Garg praised Mau's capabilities: “I think Brayden Mau is a brilliant guy... He’s a down-to-earth guy who just gets things done.”

Gomes highlighted that such research projects aim not only to provide educational experiences but also to positively impact patient outcomes: “The students are getting to learn how to use an AI system... but at the same time they are working with software engineers to understand how it can be deployed in the real world.”