arXiv Open Access 2025

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

Ayo Adedeji Mardhiyah Sanni Emmanuel Ayodele Sarita Joshi Tobi Olatunji
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (5)

A

Ayo Adedeji

M

Mardhiyah Sanni

E

Emmanuel Ayodele

S

Sarita Joshi

T

Tobi Olatunji

Format Sitasi

Adedeji, A., Sanni, M., Ayodele, E., Joshi, S., Olatunji, T. (2025). The Multicultural Medical Assistant: Can LLMs Improve Medical ASR Errors Across Borders?. https://arxiv.org/abs/2501.15310

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓