Maven at MEDIQA-CORR 2024: Leveraging RAG and Medical LLM for Error Detection and Correction in Medical Notes
Suramya Jadhav, Abhay Shanbhag, Sumedh Joshi, Atharva Date, Sheetal Sonawane
Abstract
Addressing the critical challenge of identifying and rectifying medical errors in clinical notes, we present a novel approach tailored for the MEDIQA-CORR task @ NAACL-ClinicalNLP 2024, which comprises three subtasks: binary classification, span identification, and natural language generation for error detection and correction. Binary classification involves detecting whether the text contains a medical error; span identification entails identifying the text span associated with any detected error; and natural language generation focuses on providing a free text correction if a medical error exists. Our proposed architecture leverages Named Entity Recognition (NER) for identifying disease-related terms, Retrieval-Augmented Generation (RAG) for contextual understanding from external datasets, and a quantized and fine-tuned Palmyra model for error correction. Our model achieved a global rank of 5 with an aggregate score of 0.73298, calculated as the mean of ROUGE-1-F, BERTScore, and BLEURT scores.- Anthology ID:
- 2024.clinicalnlp-1.36
- Volume:
- Proceedings of the 6th Clinical Natural Language Processing Workshop
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Danielle Bitterman
- Venues:
- ClinicalNLP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 374–381
- Language:
- URL:
- https://aclanthology.org/2024.clinicalnlp-1.36
- DOI:
- 10.18653/v1/2024.clinicalnlp-1.36
- Cite (ACL):
- Suramya Jadhav, Abhay Shanbhag, Sumedh Joshi, Atharva Date, and Sheetal Sonawane. 2024. Maven at MEDIQA-CORR 2024: Leveraging RAG and Medical LLM for Error Detection and Correction in Medical Notes. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 374–381, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Maven at MEDIQA-CORR 2024: Leveraging RAG and Medical LLM for Error Detection and Correction in Medical Notes (Jadhav et al., ClinicalNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2024.clinicalnlp-1.36.pdf