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

Legal Guidelines for Documentation01:06

Legal Guidelines for Documentation

1.3K
The legal guidelines for nursing documentation are essential for ensuring accurate, professional, and ethical recording of patient care. The guidelines are discussed here:
1.3K

You might also read

Related Articles

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

Sort by
Same author

Smartphone Keystroke Biomarkers as Predictors of Adverse Neuropsychiatric Sequelae After Trauma in Trauma Survivors: Prospective Observational Cohort Study.

Journal of medical Internet research·2026
Same author

Cuffless Noninvasive Continuous Blood Pressure Monitoring Using Superficial Temporal Arterial Tonometry.

IEEE open journal of engineering in medicine and biology·2026
Same author

Managing Recurrent Postictal Worsening of Psychosis in Clozapine-Treated Schizophrenia: A Case Report.

Case reports in psychiatry·2026
Same author

A Call to Action for Starting Clozapine: Increasing Clozapine Use and Safety in a Post-REMS Era.

Focus (American Psychiatric Publishing)·2026
Same author

Do We Now Have the Tools to Meaningfully Improve Outcomes for People With Schizophrenia?

Focus (American Psychiatric Publishing)·2026
Same author

Real-time quality feedback on Doppler data for community midwives using edge-AI.

Machine Learning. Health·2025

Related Experiment Video

Updated: Jul 12, 2025

Use of a Psychophysiological Script-driven Imagery Experiment to Study Trauma-related Dissociation in Borderline Personality Disorder
09:55

Use of a Psychophysiological Script-driven Imagery Experiment to Study Trauma-related Dissociation in Borderline Personality Disorder

Published on: March 8, 2018

12.5K

Using HIPAA (Health Insurance Portability and Accountability Act)-Compliant Transcription Services for Virtual

Salman Seyedi1, Emily Griner2, Lisette Corbin3

  • 1Department of Biomedical Informatics, Emory University, Atlanta, GA, United States.

JMIR Mental Health
|October 31, 2023
PubMed
Summary

Automatic speech recognition (ASR) transcription services show improved accuracy in mental health settings. While Amazon Transcribe performed best among ASR options, human transcription remains slightly more accurate, but ASR costs and speed offer advantages.

Keywords:
ASRHIPAAHealth Insurance Portability and Accountability ActLIWCLinguistic Inquiry and Word CountWERautomatic speech recognitionmental healthpsychiatric interviewspeech to textword error rate

More Related Videos

Development of a Virtual Reality Assessment of Everyday Living Skills
10:32

Development of a Virtual Reality Assessment of Everyday Living Skills

Published on: April 23, 2014

18.5K
Simultaneous Application of Transcranial Direct Current Stimulation during Virtual Reality Exposure
08:20

Simultaneous Application of Transcranial Direct Current Stimulation during Virtual Reality Exposure

Published on: January 18, 2021

4.0K

Related Experiment Videos

Last Updated: Jul 12, 2025

Use of a Psychophysiological Script-driven Imagery Experiment to Study Trauma-related Dissociation in Borderline Personality Disorder
09:55

Use of a Psychophysiological Script-driven Imagery Experiment to Study Trauma-related Dissociation in Borderline Personality Disorder

Published on: March 8, 2018

12.5K
Development of a Virtual Reality Assessment of Everyday Living Skills
10:32

Development of a Virtual Reality Assessment of Everyday Living Skills

Published on: April 23, 2014

18.5K
Simultaneous Application of Transcranial Direct Current Stimulation during Virtual Reality Exposure
08:20

Simultaneous Application of Transcranial Direct Current Stimulation during Virtual Reality Exposure

Published on: January 18, 2021

4.0K

Area of Science:

  • Clinical linguistics and health informatics.
  • Evaluation of automated speech recognition (ASR) for clinical transcription.

Background:

  • ASR technology is increasingly adopted for clinical transcriptions.
  • Limited research exists on comparative word error rates (WER) of different ASR services in mental health.
  • Analysis of specific word errors (omissions/commissions) by ASR in clinical contexts is underexplored.

Purpose of the Study:

  • To compare the word error rate (WER) of three ASR services (Amazon Transcribe, Zoom-Otter AI, Whisper) against a human transcription service (Rev).
  • To evaluate ASR performance across control and mental health participant groups.
  • To analyze error types in ASR transcripts using Linguistic Inquiry and Word Count categories.

Main Methods:

  • 65 participants (18 controls, 47 mental health) underwent recorded psychiatric interviews.
  • Interviews were transcribed, with researcher transcriptions serving as the gold standard for WER calculation.
  • Brunner-Munzel and Wilcoxon signed rank tests were used for statistical comparisons between services and groups.

Main Results:

  • Significant differences in WER were found among all tested ASR services (P<.001).
  • Amazon Transcribe demonstrated lower WER compared to Zoom-Otter AI and Whisper.
  • Human transcription service Rev showed a slightly lower median WER (7.6%) than Amazon Transcribe (8.9%).
  • ASR performance did not significantly differ between control and mental health groups.
  • Common ASR errors were categorized under Conversation, Cognition, and Function.

Conclusions:

  • ASR transcription accuracy is improving, narrowing the gap with human transcription.
  • Reduced cost and faster turnaround times make ASR a potentially viable healthcare option.
  • Further research is needed to assess the impact of ASR errors on clinical analysis across diverse populations.