Hearing loss affects millions worldwide, leading to social isolation, reduced work capacity, and increased mental health issues if left untreated. Comprehensive hearing evaluations are crucial for diagnosis and treatment; however, language barriers often hinder accurate assessments for non-English speakers. To address this gap, University of Wisconsin researchers are developing an AI-powered system to administer and score hearing tests in patients’ native languages.
The Challenge of Language Barriers in Hearing Healthcare
Currently, some essential hearing tests are not available in all languages, leaving healthcare providers without the necessary tools to effectively treat patients who don’t speak English fluently. This limitation can result in delayed or inaccurate diagnoses, potentially exacerbating the negative consequences of untreated hearing loss.
Developing an AI Solution for Hearing Tests
Led by Sara Misurelli, PhD, AuD, Assistant Professor in the Division of Otolaryngology-Head and Neck Surgery, and Maichou Lor, PhD, RN, Assistant Professor at the School of Nursing, the research team has received an 18-month, $150,000 Dissemination and Implementation Research Pilot Award from the UW Institute for Clinical and Translational Research. Their project focuses on creating an AI-generated, automated system for the word recognition test – a key component of hearing evaluations.
How the AI System Works
The researchers plan to develop an AI word recognition test scoring program specifically for the Hmong community. By utilizing deep learning models trained on extensive Hmong audio data, the system will be able to administer the test in patients’ primary language and accurately score the results. The team will then pilot test the program by comparing its scores with those generated by a bilingual Hmong team member.
Potential Impact on Health Equity
The successful implementation of this AI solution could significantly improve hearing healthcare for Hmong patients, a historically marginalized population in the U.S. medical system. Moreover, the project aims to create a roadmap for expanding this technology to other languages, potentially benefiting non-English speakers nationwide.
“An AI solution for word recognition tests in the Hmong language will improve hearing healthcare and promote health equity for Hmong patients,” explained Lor. “Our study will offer a roadmap for expanding this solution to other languages, which could ultimately benefit non-English speakers nationwide and allow audiologists to provide equitable healthcare in rural and underserved communities where resources for in-person interpreters may be nonexistent.”
The development of this AI-powered hearing test represents a significant step towards addressing language barriers in healthcare and promoting health equity for diverse patient populations.
