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

SBAR II: Application of SBAR01:14

SBAR II: Application of SBAR

SBAR is an effective communication tool used by healthcare professionals to communicate patient information accurately. SBAR stands for Situation, Background, Assessment, and Recommendation. For a better understanding, an example is given below.
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...

You might also read

Related Articles

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

Sort by
Same author

The Inverse Care Law in the Age of AI - Geographic Disparities in Health Care Technology Access.

NEJM AI·2026
Same author

The Role of Emergency Medical Services in Addressing Opioid Use Disorder-A Position Statement and Resource Document of NAEMSP.

Prehospital emergency care·2026
Same author

Spatiotemporal patterns of femoral fractures in older adults: healthcare access and regional inequalities in southern Brazil.

BMC geriatrics·2026
Same author

Factors associated with reporting behaviour of alcohol use in Moshi, Tanzania.

BJPsych open·2026
Same author

An Analysis of Medications for Opioid Use Disorder (MOUD) Prehospital Programs Across North Carolina.

Prehospital emergency care·2026
Same author

Spatiotemporal trends in and challenges of addressing tuberculosis in Brazil before and after the COVID-19 pandemic, 2001-2023.

Revista panamericana de salud publica = Pan American journal of public health·2026

Related Experiment Video

Updated: Jun 15, 2026

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

460

AI-based approach for transcribing and classifying unstructured emergency call data: A methodological proposal.

Dalton Breno Costa1, Felipe Coelho de Abreu Pinna2, Anjni Patel Joiner3,4

  • 1Department of Psychology, Pontifical Catholic University of Rio Grande do Sul, Rio Grande do Sul, Brazil.

PLOS Digital Health
|December 6, 2023
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) and machine learning (ML) can transcribe and classify emergency calls in Brazil. This technology offers a foundation for improved emergency medical services decision-making support.

More Related Videos

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

1.5K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K

Related Experiment Videos

Last Updated: Jun 15, 2026

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

460
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

1.5K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K

Area of Science:

  • Emergency medicine
  • Artificial intelligence
  • Natural Language Processing

Background:

  • Emergency care-sensitive conditions (ECSCs) cause over half of global deaths, necessitating rapid prehospital emergency care (PEC).
  • Unstructured emergency call data presents challenges for efficient analysis and response.
  • AI and ML applications in emergency call processing are underexplored, particularly in non-English speaking, low- and middle-income countries.

Purpose of the Study:

  • To propose and evaluate an AI/ML pipeline for transcribing, extracting, and classifying unstructured audio data from emergency calls.
  • To assess the feasibility of using open-source ML models for Portuguese-language emergency calls within the Brazilian SAMU system.

Main Methods:

  • Utilized audio data from "1-9-2" emergency calls received by SAMU Novo Norte in 2019.
  • Implemented a pipeline featuring Automatic Speech Recognition (ASR) using Wav2Vec 2.0 for Portuguese transcription and Natural Language Understanding (NLU) for call classification.
  • Trained and validated the models using manually labeled call data.

Main Results:

  • The ASR model achieved a Word Error Rate of 42.12% for transcribing Portuguese emergency calls.
  • The NLU classification model demonstrated an accuracy of 73.9% in categorizing calls within a validation subset.
  • The study highlights the potential of AI for processing emergency call data in resource-limited settings.

Conclusions:

  • AI and ML models can effectively transcribe and classify unstructured emergency call data in Brazilian emergency medical services.
  • This approach serves as a crucial first step toward developing AI-powered decision-making support tools for emergency response.
  • Further research is needed to adapt and optimize ML models for diverse linguistic and operational contexts in emergency care.