Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Incidence, contributing factors, and predictors of diagnostic errors in medical inpatients: A retrospective cohort study.

Journal of hospital medicine·2026
Same author

Extracorporeal Membrane Oxygenation (ECMO) for Acute Respiratory Distress Syndrome (ARDS) During Pregnancy: A Systematic Review.

Cureus·2026
Same author

Polytrauma in the elderly: who is at risk? A case-control study.

BMC geriatrics·2026
Same author

Patient safety incidents associated with EMR use: Results of a national survey of Swiss physicians.

Digital health·2026
Same author

Large Language Model-Based Patient Simulation to Foster Communication Skills in Health Care Professionals: User-Centered Development and Usability Study.

JMIR medical education·2025
Same author

First Breath Matters: Out-of-Hospital Mechanical Ventilation in Patients with Traumatic Brain Injury.

Journal of clinical medicine·2025
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

Related Experiment Video

Updated: May 14, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.3K

AI-Enhanced Speech Recognition in Triage.

Ahmed Elhilali1, Vanessa Brügger1, Isabelle Tschannen2

  • 1Bern University of Applied Sciences, Institute for Medical Informatics.

Studies in Health Technology and Informatics
|May 6, 2025
PubMed
Summary
This summary is machine-generated.

An AI system using speech recognition and large language models shows high accuracy in assigning emergency triage levels and complaint classifications, despite challenges with Swiss German dialects. This technology could improve emergency department efficiency.

Keywords:
Artificial IntelligenceEmergency MedicineNatural Language Processing (NLP)Speech-to-TextTriageTriage Systems

More Related Videos

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

380
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

312

Related Experiment Videos

Last Updated: May 14, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.3K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

380
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

312

Area of Science:

  • Emergency Medicine
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Triage in emergency departments is crucial for timely patient care but faces challenges in accuracy and efficiency due to high demand and time constraints.
  • Existing triage systems can be subjective and time-consuming, leading to potential delays in patient treatment.

Purpose of the Study:

  • To evaluate a proof-of-concept AI-powered triage system utilizing speech-to-text (STT) and large language models (LLMs).
  • To assess the system's ability to assign Emergency Severity Index (ESI) levels and Canadian Emergency Department Information System (CEDIS) complaint classifications.
  • To investigate the impact of Swiss German dialects on AI performance in triage.

Main Methods:

  • The study employed STT and LLMs to process patient interactions during triage.
  • The AI system was designed to assign ESI levels and CEDIS complaint classifications.
  • Performance was evaluated using word error rates (WER) for STT and classification accuracy for ESI and CEDIS codes, considering different German dialects.

Main Results:

  • STT models achieved low WER for High German (2.3%) but higher WER for Swiss German (17.66%).
  • Despite STT challenges, the AI system demonstrated high classification accuracy, ranging from 90-100% for ESI levels and CEDIS codes.
  • The AI system showed potential in standardizing triage assessments and reducing documentation workload.

Conclusions:

  • AI integration, leveraging STT and LLMs, holds significant potential for enhancing triage consistency and efficiency in emergency departments.
  • The system's accuracy in classification, even with dialectal variations, suggests a promising application in clinical workflows.
  • Future research should focus on multi-language adaptation and robust data security for real-world implementation.