Language Translation Apps in Health Care Settings: Expert Opinion
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: Currently, over 300 languages are spoken in Australian homes. People without proficient English from non-English speaking countries may not receive equitable care if their health care workers do not speak their primary language. Use of professional interpreters is considered the gold standard; however, for a variety of reasons, it is often limited to key aspects of care such as diagnosis and consent. With the emergence of mobile technologies, health care workers are increasingly using digital translation tools to fill this gap. However, many of these technologies have not been developed for health care settings and their use has not been evaluated. OBJECTIVE: This study aimed to evaluate iPad-compatible language translation apps to determine their suitability for enabling everyday conversations in health care settings. METHODS: Translation apps were identified by searching the Apple iTunes Store and published and grey literature. Criteria for inclusion were that the apps were available at no cost, able to translate at least one of the top 10 languages spoken in Australia, and available for use on iPad. Apps that met inclusion criteria were reviewed in 2 stages. Stage 1 was the feature analysis conducted by 2 independent researchers, where apps were evaluated for offline use, input and output methods, and number of languages. Stage 2 was the analysis of suitability for everyday communication in the health care setting, conducted by 2 independent professionals with expertise in translation and cross-cultural communication. Apps that enabled key aspects of care normally within the realm of professional interpreters, such as assessment, treatment and discharge planning, and seeking consent for medical treatments, were considered unsuitable. RESULTS: In total, 15 apps were evaluated. Of these, 8 apps contained voice-to-voice and voice-to-text translation options. In addition, 6 apps were restricted to using preset health phrases, whereas 1 app used a combination of free input and preset phrases. However, 5 apps were excluded before stage 2. In addition, 6 of the 10 remaining apps reviewed in stage 2 were specifically designed for health care translation purposes. Of these, 2 apps were rated as suitable for everyday communication in the health care setting-culturally and linguistically diverse Assist and Talk To Me. Both apps contained simple and appropriate preset health phrases and did not contain conversations that are normally within the realm of professional interpreters. CONCLUSIONS: All iPad-compatible translation apps require a degree of caution and consideration when used in health care settings, and none should replace professional interpreters. However, some apps may be suitable for everyday conversations, such as those that enable preset phrases to be translated on subject matters that do not require a professional interpreter. Further research into the use of translation technology for these types of conversations is needed.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it