Written by It may someday be possible to use Large Language Models (LLM) to automatically read clinical notes in medical records and reliably and efficiently extract relevant information to support patient care or research. But recent research from Columbia University Mailman School of Public Health using ChatGPT-4 to read medical notes from Emergency Department admissions to determine whether injured scooter and bicycle riders were wearing a helmet finds that LLM can’t yet do this reliably. The findings are published in JAMA Network Open.
Medical Xpress – latest medical and health news stories