Add to Favourites
To login click here
This article discusses the potential use of generative artificial intelligence (AI) to extract information from unstructured clinical notes in electronic medical records. The study found that while there are potential efficiency gains, issues of reliability and hallucinations currently limit its utility. The study used a large language model (LLM) called ChatGPT-4 to analyze clinical narratives and identify helmet use status of patients injured in micromobility-related accidents. The LLM had weak to moderate agreement with a text string-search approach and was not able to perfectly replicate its analyses across new sessions and days.