Dataset Information

A Speech-Enabled Fixed-Phrase Translator for Emergency Settings: Crossover Study.

ABSTRACT: BACKGROUND:In the context of the current refugee crisis, emergency services often have to deal with patients who have no language in common with the staff. As interpreters are not always available, especially in emergency settings, medical personnel rely on alternative solutions such as machine translation, which raises reliability and data confidentiality issues, or medical fixed-phrase translators, which sometimes lack usability. A collaboration between Geneva University Hospitals and Geneva University led to the development of BabelDr, a new type of speech-enabled fixed-phrase translator. Similar to other fixed-phrase translators (such as Medibabble or UniversalDoctor), it relies on a predefined list of pretranslated sentences, but instead of searching for sentences in this list, doctors can freely ask questions. OBJECTIVE:This study aimed to assess if a translation tool, such as BabelDr, can be used by doctors to perform diagnostic interviews under emergency conditions and to reach a correct diagnosis. In addition, we aimed to observe how doctors interact with the system using text and speech and to investigate if speech is a useful modality in this context. METHODS:We conducted a crossover study in December 2017 at Geneva University Hospitals with 12 French-speaking doctors (6 doctors working at the outpatient emergency service and 6 general practitioners who also regularly work in this service). They were asked to use the BabelDr tool to diagnose two standardized Arabic-speaking patients (one male and one female). The patients received a priori list of symptoms for the condition they presented with and were instructed to provide a negative or noncommittal answer for all other symptoms during the diagnostic interview. The male patient was standardized for nephritic colic and the female, for cystitis. Doctors used BabelDr as the only means of communication with the patient and were asked to make their diagnosis at the end of the dialogue. The doctors also completed a satisfaction questionnaire. RESULTS:All doctors were able to reach the correct diagnosis based on the information collected using BabelDr. They all agreed that the system helped them reach a conclusion, even if one-half felt constrained by the tool and some considered that they could not ask enough questions to reach a diagnosis. Overall, participants used more speech than text, thus confirming that speech is an important functionality in this type of tool. There was a negative association (P=.02) between the percentage of successful speech interactions (spoken sentences sent for translation) and the number of translated text items, showing that the doctors used more text when they had no success with speech. CONCLUSIONS:In emergency settings, when no interpreter is available, speech-enabled fixed-phrase translators can be a good alternative to reliably collect information from the patient.

SUBMITTER: Spechbach H

PROVIDER: S-EPMC6528434 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Speech-Enabled Fixed-Phrase Translator for Emergency Settings: Crossover Study.

Spechbach Hervé H Gerlach Johanna J Mazouri Karker Sanae S Tsourakis Nikos N Combescure Christophe C Bouillon Pierrette P

JMIR medical informatics 20190507 2

<h4>Background</h4>In the context of the current refugee crisis, emergency services often have to deal with patients who have no language in common with the staff. As interpreters are not always available, especially in emergency settings, medical personnel rely on alternative solutions such as machine translation, which raises reliability and data confidentiality issues, or medical fixed-phrase translators, which sometimes lack usability. A collaboration between Geneva University Hospitals and ...[more]

PMID: 31066702

Similar Datasets

Project description:Severe sepsis is a time critical condition which is known to have a high mortality rate. Evidence suggests that early diagnosis and early administration of antibiotics can reduce morbidity and mortality from sepsis. The prehospital phase of emergency medical care may provide the earliest opportunity for identification of sepsis and delivery of life-saving treatment for patients. We aimed to assess the feasibility of (1) paramedics recognising and screening patients for severe sepsis, collecting blood cultures and administering intravenous antibiotics; and (2) trial methods in order to decide whether a fully-powered trial should be undertaken to determine safety and effectiveness of this intervention. Paramedics were trained in using a sepsis screening tool, aseptic blood culture collection and administration of intravenous antibiotics. If sepsis was suspected, paramedics randomly allocated patients to intervention or usual care using scratchcards. Patients were followed up at 90 days using linked anonymised data to capture length of hospital admission and mortality. We collected self-reported health-related quality of life at 90 days. We pre-specified criteria for deciding whether to progress to a fully-powered trial based on: recruitment of paramedics and patients; delivery of the intervention; retrieval of outcome data; safety; acceptability; and success of anonymised follow-up. Seventy-four of the 104 (71.2%) eligible paramedics agreed to take part and 54 completed their training (51.9%). Of 159 eligible patients, 146 (92%) were recognised as eligible by study paramedics, and 118 were randomised (74% of eligible patients, or 81% of those recognised as eligible). Four patients subsequently dissented to be included in the trial (3%), leaving 114 patients recruited to follow-up. All recruited patients were matched to routine data outcomes in the Secure Anonymised Information Linkage Databank. Ninety of the 114 (79%) recruited patients had sepsis or a likely bacterial infection recorded in ED. There was no evidence of any difference between groups in patient satisfaction, and no adverse reactions reported. There were no statistically significant differences between intervention and control groups in Serious Adverse Events (ICU admissions; deaths). This feasibility study met its pre-determined progression criteria; an application will therefore be prepared and submitted for funding for a fully-powered multi-centre randomised trial.Trial registration: ISRCTN36856873 sought 16th May 2017; https://doi.org/10.1186/ISRCTN36856873.

Project description:ObjectivesRates of unused ('idle') peripheral intravenous catheters (PIVCs) are high but can vary per setting. Understanding factors that influence the decision-making of doctors, nurses and paramedics in the emergency setting regarding PIVC insertion, and what factors may modify their decision is essential to identify opportunities to reduce unnecessary cannulations and improve patient-centred outcomes. This study aimed to understand factors associated with clinicians' decision-making on whether to insert or use a PIVC in the emergency care setting.DesignA qualitative descriptive study using in-depth semistructured interviews and thematic analysis.SettingGold Coast, Queensland, Australia, in a large tertiary level emergency department (ED) and local government ambulance service.ParticipantsParticipants recruited were ED clinicians (doctors, nurses) and paramedics who regularly insert PIVCs.ResultsFrom the 15 clinicians interviewed 4 key themes: knowledge and experience, complicated and multifactorial, convenience, anticipated patient clinical course, and several subthemes emerged relating to clinician decision-making across all disciplines. The first two themes focused on decision-making to gather data and evidence, such as knowledge and experience, and decisions being complicated and multifactorial. The remaining two themes related to the actions clinicians took such as convenience and anticipated patient clinical course.ConclusionThe decision to insert a PIVC is more complicated than clinicians, administrators and policy-makers may realise. When explored, clinician decisions were multifaceted with many factors influencing the decision to insert a PIVC. In actual practice, clinicians routinely insert PIVCs in most patients as a learnt reflex with little cognitive input. When considering PIVC insertion, more time needs to be devoted to the awareness of: (1) decision-making in the context of the clinician's own experience, (2) cognitive biases and (3) patient-centred factors. Such awareness will support an appropriate risk assessment which will benefit the patient, clinician and healthcare system.

Dataset Information

A Speech-Enabled Fixed-Phrase Translator for Emergency Settings: Crossover Study.

Publications

A Speech-Enabled Fixed-Phrase Translator for Emergency Settings: Crossover Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets