In this task, we seek to address the problem of identifying and correcting (common sense) medical errors in clinical notes. From a human perspective, these errors require medical expertise and knowledge to be both identified and corrected.
We used OpenAI's GPT-4 API with RAG for error detection and sentence correction.
- This code used Azure OAI GPT API
- Ensure the dataset can be found
- Necessary installations are provided at the top of the notebooks
- Run the scripts
@inproceedings{
anonymous2024emmixers,
title={{EM}\_Mixers at {MEDIQA}-{CORR} 2024: Knowledge-Enhanced Few-Shot In-Context Learning for Medical Error Detection \& Correction},
author={Swati Rajwal, Eugene Agichtein, Abeed Sarker},
booktitle={The 6th Clinical Natural Language Processing Workshop},
year={2024},
url={https://openreview.net/forum?id=ygrXEObZLD}
}