Sumedh Joshi


2024

pdf bib
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
Proceedings of the 6th Clinical Natural Language Processing Workshop

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.