Large Language Models for Extraction of Structured Data in Pathology
This repository contains a comprehensive suite of scripts designed to extract, process, analyze, and visualize structured data from pathology reports. The workflow utilizes various models and APIs, including OpenAI's GPT-4, Hugging Face's LLaMA models, and 4-bit quantized model versions provided by Ollama. Additionally, R scripts are provided for detailed statistical analysis and visualization of the extracted data.
Institutions
- University Hospital Cologne (DE)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2024-09-04
- DOI
- https://doi.org/10.5281/zenodo.13685449
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00