Buffalo, N.Y.-based Roswell Park Comprehensive Cancer Center and the University at Buffalo have developed an AI tool to assess lung cancer patients’ risk of postoperative complications.
The model combines clinical data, CT imaging and large language model-generated explanations to provide personalized risk estimates and clinician-adjustable summaries, according to an April 27 news release.
Researchers evaluated the tool using data from 3,094 patients who underwent surgery between 2009 and 2023. The model identified complications with 75-80% sensitivity, compared to about 45% for thoracic surgeons.
The top-performing version also achieved about 81% accuracy in distinguishing higher- from lower-risk patients while maintaining low false-positive rates.
The tool is designed to support surgical decision-making by integrating patient-specific data with clinician input and may be expanded to other specialties following further validation.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
