The Multicultural Medical Assistant: Can LLMs Improve Medical ASR Errors Across Borders?

TL;DR

This paper examines how Large Language Models can reduce medical transcription errors caused by accents and terminology across Nigeria, the UK, and the US, highlighting regional disparities and conditions for effective correction.

Contribution

It provides a cross-regional analysis of LLM effectiveness in correcting ASR errors in medical transcription, addressing accent and terminology challenges.

Findings

Significant regional disparities in ASR accuracy.

LLMs improve transcription accuracy under specific conditions.

Accent and terminology influence correction effectiveness.

Abstract

The global adoption of Large Language Models (LLMs) in healthcare shows promise to enhance clinical workflows and improve patient outcomes. However, Automatic Speech Recognition (ASR) errors in critical medical terms remain a significant challenge. These errors can compromise patient care and safety if not detected. This study investigates the prevalence and impact of ASR errors in medical transcription in Nigeria, the United Kingdom, and the United States. By evaluating raw and LLM-corrected transcriptions of accented English in these regions, we assess the potential and limitations of LLMs to address challenges related to accents and medical terminology in ASR. Our findings highlight significant disparities in ASR accuracy across regions and identify specific conditions under which LLM corrections are most effective.