Using artificial intelligence based language interpretation in non-urgent paediatric emergency consultations: a clinical performance test and legal evaluation.
Publisher DOI
PubMed ID
39856756
Abstract
Objective
To evaluate the accuracy of Google Translate (GT) in translating low-acuity paediatric emergency consultations involving respiratory symptoms and fever, and to examine legal and policy implications of using AI-based language interpretation in healthcare.
Methods
Based on the methodology used for conducting language performance testing routinely at the Interpreter Services Department of the Hospital for Sick Children, clinical performance testing was completed using a paediatric emergency scenario (child with respiratory illness and fever) on five languages: Spanish, French, Urdu, Arabic, and Mandarin. The study focused on GT's translation accuracy and a legal and policy evaluation regarding AI-based interpretation in healthcare was conducted by legal scholars.
Results
GT demonstrated strong translation performance, with accuracy rates from 83.5% in Urdu to 95.4% in French. Challenges included dialect sensitivity and pronoun misinterpretations. Legal evaluation indicated inconsistent access to language interpretation services across healthcare jurisdictions and potential risks involving data privacy, consent, and malpractice when using AI-based translation tools.
Conclusions
Google Translate can effectively support communication in specific non-critical paediatric emergency scenarios. However, its use necessitates careful monitoring, understanding of its limitations, and attention to dialect and literal translation risks along with equity considerations. Establishing legal and policy frameworks for language interpretation in healthcare is crucial, alongside addressing funding and data security concerns, to optimize the use of AI-based translation tools in healthcare contexts.
To evaluate the accuracy of Google Translate (GT) in translating low-acuity paediatric emergency consultations involving respiratory symptoms and fever, and to examine legal and policy implications of using AI-based language interpretation in healthcare.
Methods
Based on the methodology used for conducting language performance testing routinely at the Interpreter Services Department of the Hospital for Sick Children, clinical performance testing was completed using a paediatric emergency scenario (child with respiratory illness and fever) on five languages: Spanish, French, Urdu, Arabic, and Mandarin. The study focused on GT's translation accuracy and a legal and policy evaluation regarding AI-based interpretation in healthcare was conducted by legal scholars.
Results
GT demonstrated strong translation performance, with accuracy rates from 83.5% in Urdu to 95.4% in French. Challenges included dialect sensitivity and pronoun misinterpretations. Legal evaluation indicated inconsistent access to language interpretation services across healthcare jurisdictions and potential risks involving data privacy, consent, and malpractice when using AI-based translation tools.
Conclusions
Google Translate can effectively support communication in specific non-critical paediatric emergency scenarios. However, its use necessitates careful monitoring, understanding of its limitations, and attention to dialect and literal translation risks along with equity considerations. Establishing legal and policy frameworks for language interpretation in healthcare is crucial, alongside addressing funding and data security concerns, to optimize the use of AI-based translation tools in healthcare contexts.
Date Issued
2025-01-24
Publication Type
Article
Subject(s)
Subjects
Artificial intelligence
•
Minor health visits
•
Non-urgent health visits
•
Pediatric emergency medicine
•
Pediatric migrant health
•
Pediatrics
Language(s)
en
Author(s)
Stedman, Ian | |
Stancati, Noah | |
Sappleton, Karen | |
Kanathasan, Sarathy | |
Fayyaz, Jabeen | |
Singh, Devin |
Additional Credits
Journal
BMC Health Services Research
Publisher
BioMed Central
ISSN
1472-6963
Access(Rights)
open.access