AI Algorithm Predicts Weight Loss After Radiation for Head... : Oncology Times

CHICAGO--An artificial intelligence machine-learning program has demonstrated the ability to accurately forecast which head and neck cancer patients are likely to experience severe weight loss, necessitating the use of a feeding tube, researchers at MD Anderson Cancer Center in Houston told attendees at the 2019 ASTRO Annual Meeting (Abstract 141). It marks the first time that such a sophisticated "self-teaching" computer algorithm has accurately identified patients likely to develop problems eating, said Jay Reddy, MD, PhD, Assistant Professor of Radiation Oncology and lead author of the study. "With head and neck radiation, a lot of toxicity occurs; however it's not always clear which patients will experience serious side effects," he told a press conference. Reddy and his colleagues used machine learning models to analyze large datasets from three sources--electronic health records, an internal web-based patient charting tool, and the hospital's records and verification system--in an effort to discern and eventually predict patients with weight loss exceeding 10 percent of total body weight, the need for a feeding tube, and/or any unplanned hospitalization within 3 months of radiation. Machine learning is a relatively powerful application of artificial intelligence (AI)–think facial recognition software--by which a computer program can automatically learn and improve itself by analyzing large quantities of data.