AI Insight
Researchers have developed a large language model-based system to identify cardiac events in electronic health records of cancer patients. The system addresses the challenge of detecting cardiotoxicity in breast and lung cancer patients, who face elevated heart-related risks due to cancer treatments affecting organs near the heart. This automated approach overcomes the impracticality of manually reviewing hundreds of patient records to find evidence of cardiac disease.
Why it matters
This technology could enable earlier detection and monitoring of heart complications in cancer patients undergoing treatment, potentially improving patient outcomes through timely intervention. The automated system makes it feasible to screen large patient populations for cardiotoxicity that would otherwise go undetected due to resource constraints.
Understand the Science
Patients with breast and lung cancer are at increased risk of cardiotoxicity, or heart-related damage caused by cancer treatments, because of the proximity of the heart, lungs and breasts. Cardiotoxicity increases the risk of heart attacks, heart failure and other cardiac conditions. Looking for evidence of cardiac disease in these patients requires reading through hundreds of patients’ health records, which is often too time-consuming to be practical.