Can LangExtract Turn Messy Clinical Notes into Structured Data?

LangExtract is a new open-source tool that leverages large language models to convert unstructured text into clean, structured data. The process involves defining a task with a prompt, providing a few high-quality examples, and then running the extraction. A key use case explored is the challenging task of identifying adverse drug reactions (ADRs), medications, and dosages from complex clinical notes. The tool demonstrates effectiveness in this area by correctly distinguishing ADRs from pre-existing conditions. LangExtract is flexible, supporting proprietary models like Gemini as well as local models through Ollama for various information extraction needs.