Large language model-based system identifies cardiac event data in cancer patients' electronic health records
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…
This study, published in the International Journal of Radiation Oncology, Biology, Physics, introduces an LLM-based system for identifying cardiac event data in the electronic health records of patients with breast and lung cancer.
Cancer treatments, such as radiation therapy, can cause cardiotoxicity, which increases the risk of heart attacks, heart failure, and other cardiac conditions. Manually reviewing EHRs to look for evidence of cardiac disease is time-consuming and impractical.
Researchers from Thomas Jefferson University trained an LLM to extract cardiac event data from patient EHRs. The LLM identified cardiac events 71% to 85.5% of the time, while humans took about two hours to review each EHR. The LLM also accounted for negated events, where the patient denied a specific disease.
The study's lead author, Wenchao Cao, highlights the potential of this LLM to streamline cardiotoxicity surveillance and inform personalized radiation therapy plans, potentially improving patient outcomes and reducing side effects.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
