Health
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.
AI Summary
A study evaluated large language model–based systems for identifying cardiac events in cancer patients’ electronic health records. In the initial screening, general‑purpose reasoning models—including DeepSeek‑R1‑70b, Llama‑3.3, and Mistral‑Large—showed both high diagnostic accuracy and near‑perfect adherence to required formatting. These three models were selected for further testing in validation cohorts. The work appears in the Journal of Radiation Oncology Biology Physics.
Read full article on Medical XpressAI summaries can be wrong sometimes—always verify important details using the source article.
How AI & Automation are usedMore from Health
Continue reading recent Health coverage
- Psychologists investigate how first impressions influence impressions of trustworthinessContinue reading
- Buprenorphine treatment differs in urban, rural areasContinue reading
- HHS spins a tale of a would-be content creator childContinue reading
- Whatever happened to ... children infected with HIV due to failures in healthcare?Continue reading
Support HappeningNow
Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.
Support HappeningNow