Using artificial intelligence based language interpretation in non-urgent paediatric emergency consultations: a clinical performance test and legal evaluation
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.041 | 0.181 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".