Retrieval-Augmented Generation Based Nurse Observation Extraction

TL;DR

This paper presents a Retrieval-Augmented Generation method to automatically extract clinical observations from nurse dictations, reducing nurses' workload with high accuracy.

Contribution

It introduces a novel RAG-based pipeline specifically designed for extracting clinical observations from medical dictations.

Findings

Achieved an F1-score of 0.796 on MEDIQA-SYNUR dataset.

Demonstrated effective performance in clinical observation extraction.

Reduces manual workload for nurses.

Abstract

Recent advancements in Large Language Models (LLMs) have played a significant role in reducing human workload across various domains, a trend that is increasingly extending into the medical field. In this paper, we propose an automated pipeline designed to alleviate the burden on nurses by automatically extracting clinical observations from nurse dictations. To ensure accurate extraction, we introduce a method based on Retrieval-Augmented Generation (RAG). Our approach demonstrates effective performance, achieving an F1-score of 0.796 on the MEDIQA-SYNUR test dataset.