MétaCan
Menu
Back to cohort
Record W4403475292 · doi:10.2196/63095

Digital Translation Platform (Translatly) to Overcome Communication Barriers in Clinical Care: Pilot Study

2024· article· en· W4403475292 on OpenAlexvenueno aff
Victor Olsavszky, Mutaz Bazari, Taieb Ben Dai, Ana Olsavszky, Fabian Finkelmeier, Stefan Zeuzem, Eva Herrmann, Jan Leipe, Florian Alexander Michael, Hans von Westernhagen, Olivier Balló

Bibliographic record

VenueJMIR Formative Research · 2024
Typearticle
Languageen
FieldHealth Professions
TopicInterpreting and Communication in Healthcare
Canadian institutionsnot available
Fundersnot available
KeywordsPreprintTranslation (biology)Computer scienceHuman–computer interactionWorld Wide WebBiology

Abstract

fetched live from OpenAlex

BACKGROUND: Language barriers in health care can lead to misdiagnosis, inappropriate treatment, and increased medical errors. Efforts to mitigate these include using interpreters and translation tools, but these measures often fall short, particularly when cultural nuances are overlooked. Consequently, medical professionals may have to rely on their staff or patients' relatives for interpretation, compromising the quality of care. OBJECTIVE: This formative pilot study aims to assess the feasibility of Translatly, a digital translation platform, in clinical practice. Specifically, the study focuses on evaluating (1) how health care professionals overcome language barriers and their acceptance of an on-demand video telephony platform, (2) the feasibility of the platform during medical consultations, and (3) identifying potential challenges for future development. METHODS: The study included ethnographic interviews with health care professionals and an observational pilot to assess the use of the Translatly platform in clinical practice. Translatly was developed to make real-time translation easy and accessible on both Android and iOS devices. The system's backend architecture uses Java-based services hosted on DigitalOcean. The app securely exchanges data between mobile devices and servers, with user information and call records stored in a MySQL database. An admin panel helps manage the system, and Firebase integration enables fast push notifications to ensure that health care professionals can connect with translators whenever they need to. The platform was piloted in a German university hospital with 170 volunteer nonprofessional translators, mainly medical students, supporting translation in over 20 languages, including Farsi, Dari, and Arabic. RESULTS: Ethnographic research conducted by interviewing health care professionals in Frankfurt am Main and other German cities revealed that current practices for overcoming language barriers often rely on family members or digital tools such as Google Translate, raising concerns about accuracy and emotional distress. Respondents preferred an on-demand translation service staffed by medically experienced translators, such as medical students, who understand medical terminology and can empathize with patients. The observational pilot study recorded 39 requests for translation services, 16 (41%) of which were successfully completed. The translations covered 6 different languages and were carried out by a team of 10 translators. Most requests came from departments such as infectious diseases (5/16, 31%) and emergency (4/16, 25%). Challenges were identified around translator availability, with 23 (59%) total requests (N=39) going unanswered, which was further evidenced by user feedback. CONCLUSIONS: This pilot study demonstrates the feasibility of the Translatly platform in real-world health care settings. It shows the potential to improve communication and patient outcomes by addressing language barriers. Despite its potential, challenges such as translator availability highlight the need for further development.

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 distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesResearch integrity, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.126
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0070.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.004
Insufficient payload (model declined to judge)0.0000.001

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.

Opus teacher head0.310
GPT teacher head0.602
Teacher spread0.292 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designQualitative
Domainnot available
GenreEmpirical

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".

Quick stats

Citations8
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative ResearchSame topicInterpreting and Communication in HealthcareFrench-language works237,207