![]() ![]() ![]() Although different evaluations of medical devices have been conducted, to the best of our knowledge, this is the first study that attempts to show the impact of “phraselators” on the diagnosis and to define a methodology to achieve this. It aims to determine whether this type of restricted translation tool can be used by doctors to perform a diagnostic interview and reach a correct diagnosis and to quantify if speech adds value to fixed-phrase translators. This study is the first step in this direction. It was also designed as a way to collect doctor-patient dialogues and thereby improve our understanding of the criteria for the development of this type of system. This tool is a compromise between speech-to-speech machine translation and fixed-phrase translation systems and directly addresses specific needs in emergency settings (ie, high accuracy, extensibility, portability to low-resource languages and domains, and data security). As emphasized in the recent review by Dew et al, there is a lack of criteria for the development and evaluation of these systems, which impedes the adoption of these systems in emergency settings.įor these reasons, we have developed a new type of speech-enabled fixed-phrase translation tool for medical dialogue (BabelDr ), based on our previous experience in the field in a collaborative venture between HUG and the University of Geneva Faculty of Translation and Interpreting. A plethora of specialized systems have also been developed for medical communication, both in the academic and industry settings (including fixed-phrase translation or machine translation systems ), but it is not always clear how they were built or evaluated and if they are extensible. However, such systems also pose ethical problems and are not currently compatible with the Swiss Data Protection Law. ![]() Some recent studies have estimated that nearly 40% of sentences of medical speech translated by Google Translate are mistranslated. Machine translation, such as Google Translate, another low-cost solution more commonly used in emergency contexts, is also extremely problematic, as this type of tool has not been developed for medical use. Asking patients’ relatives to translate speech is known to create substantial risks. Phone-based interpreter services, which are the most common solution, are generally considered adequate, but they are expensive (3 Swiss francs/minute with AOZ Medios, a national interpreting service mandated by the Swiss Federal Office of Public Health), not always available for some languages, and less satisfactory than face-to-face interaction with a physically present interpreter. Both ethically and legally, hospitals have a duty to offer all patients the same quality of care, including the right to have a dialogue with health professionals.ĭifferent solutions are available for use in emergency settings to address these language barriers, but they all have their drawbacks. For example, as reported by Rechel et al in 2003, the United States Institute for Healthcare Advancement estimated that US $73 billion was wasted annually in the United States as a result of communication problems in health care, many of which originate from language differences. This language barrier situation is known to pose many safety and ethical problems: It is responsible for increased risks for patients and is very expensive. Taken together, these languages represent 75% of the interpreting hours at HUG (Geneva University Hospitals, personal communication, 2017). In 2017, the 10 languages for which interpretation services were the most solicited were Tigrinya, Tamil, Albanian, Farsi, Spanish, Somalian, Syrian, Dari, Portuguese, and Arabic (North Africa). For example, at Geneva University Hospitals (HUG), 52% of patients are foreigners and 10% speak no French at all. In the context of the current refugee crisis, emergency services are increasingly confronted with patients who have no language in common with staff and may not share the same culture. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |