Survey-Based Evaluation of an Innovative Speech-Enabled Translator in Emergency Settings: A Phase II Cohort Study

Aims of the study: Healthcare systems worldwide are more and more confronted with migrant patients and associated language barriers. Literature shows a potential decrease in quality of care in hospitals due to language barriers. The gold standard in these situations is to use a professional interpreter during consultations, but this solution can be difficult in emergency settings where time is of the essence. With modern technology, automatic translation tools such as Google Translate are available, but they are not precise enough for use in the medical context. Our aim is to evaluate the perceived efficacy and technical features of a speech-enabled, fixed-phrase translation tool “Babel Dr.” in an emergency department. Methods: We conducted a phase II cohort study using a survey-based design to assess patient and physician satisfaction and perceived efficacy of the technical features of the tool in real life situations. Thirty of 42 eligible allophone patients visiting an outpatient emergency unit mean age, 38.2 [standard deviation, 16.49] years; 53.3% (n=16) were male were included. Selected patients had no understanding of the French language. Physicians were assigned if they did not have a common language with the patients. Results: Regarding satisfaction, 90% (n=27) of patients and 86.6% (n=26) of physicians had a positive impression of the translation tool. In addition, 90% (n=27) of patients felt able to tell the physician why they came to the emergency room and 93.3% (n=28) expressed that they understood the tool’s translations. Forty percent (n=12) of patients also stated that they would not have preferred to use an interpreter during the consultation. Regarding the perceived efficacy, 93.3% (n=28) of physicians affirmed that they could understand the patient’s health problem and 80% (n=24) were able to make a diagnosis. A significant positive association (P<0.05) was observed between physicians’ appreciation of the different features of the tool and their overall satisfaction. Conclusion: Our study suggests that the fixed-phrase translation system Babel Dr. is suited for diagnostic interviews in an emergency context and a valid alternative when no interpreter is available. Trial registration: ClinicalTrials.gov ID NCT04788966. Registered 04 Mars 2021, https://clinicaltrials.gov/ct2/show/NCT04788966