Congratulations to our graduate student Ethan Stolen and Assistant Professor of Radiation Oncology James Sohn on having their abstract selected for the prestigious Best in Physics designation at the upcoming 2026 American Association of Physicists in Medicine (AAPM) meeting. For this outstanding work, they were joined by researchers at the UChicago Data Science Institute, the University of Wisconsin-Madison, and Virginia Commonwealth University.
Their research represents a novel application of artificial intelligence to analyze the reliability of the linear accelerators (LINACs) that are used daily to treat cancer patients. The work utilized 10 years of maintenance records from UChicago Medicine’s four LINACs, representing one of the largest and most comprehensive datasets of maintenance records published by any institution.
Their study demonstrates how Large Language Models (LLMs) can transform extensive, decade-long unstructured maintenance records into clear, actionable insights regarding equipment failure patterns and downtime causes. This makes their work one of the longest, most complete analyses of LINAC maintenance records to date.
This data-driven approach directly informs maintenance strategies and inventory management at UChicago Medicine, ensuring higher machine availability and uninterrupted patient care. Their innovative methods highlight UChicago Medicine’s commitment to using data to improve the quality and consistency of radiation therapy.
If you are attending the 2026 AAPM meeting, please stop by the following sessions to see their work:
Best in Physics Poster Session
- Date: Monday, July 20, 2026
- Time: 3:15 PM – 4:00 PM
- Location: Best in Physics Poster Theater area, Exhibit Hall
Oral Presentation
- Session: Therapy Physics Scientific Session: Modern Tools for a Safe Clinic
- Date: Tuesday, July 21, 2026
- Time: 4:00 PM
- Location: Room 118