Unlocking the potential of free text in electronic health records with large language models (LLM): enhancing patient safety and consultation interactions.

Detailed free-text information is collected and recorded in the EHR during primary care consultations, but much of it isn't fully used. This review highlights current challenges with and potential solutions for using large language models (LLMs) to transform clinical notes into rich data sources. LLMs can process free-text information to improve patient care, identify potential issues, and enhance patient-provider communication. Significant LLM fine-tuning and training would be required to make this process more effective.