Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Generalized Anxiety Disorder

Generalized Anxiety Disorder

Generalized Anxiety Disorder (GAD) is a chronic condition characterized by excessive and uncontrollable worry that persists for at least six months, significantly interfering with daily functioning. Unlike situational anxiety, which arises in response to specific stressors, GAD often occurs without a clear cause. Individuals may experience disproportionate worry about work, health, or relationships. For instance, a person might continuously fear poor health despite normal medical evaluations or...

Social Anxiety Disorder

Social Anxiety Disorder

Social anxiety disorder, also known as social phobia, is characterized by an intense fear of social situations where one might face humiliation, rejection, embarrassment, or negative evaluation. This disorder leads individuals to avoid activities like casual conversations, public speaking, or seemingly simple tasks such as eating, signing documents, or swimming, in public settings. Its impact extends beyond discomfort, often significantly interfering with daily functioning and quality of life.

Anxiety: Overview

Anxiety: Overview

Anxiety is a common mental disorder featuring excessive worry, fear, and apprehension, significantly affecting daily life. People with anxiety disorders experience persistent and intense anxiety, interrupting their everyday functioning.
Individuals with anxiety often experience a range of physical and emotional symptoms, including sweating, trembling, tachycardia, and disturbances in sleep patterns. These symptoms vary in intensity and frequency but are generally disruptive and distressing.

You might also read

Related Articles

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

Sort by

Same author

Digital Health Monitoring and Intervention Suite for Stress in Frontline Nurses: Prospective Cohort Trial.

JMIR formative research·2026

Same author

Testing the Acceptability and Feasibility of a Gender-Informed Smoking Cessation mHealth App for Women: Mixed Methods Approach.

JMIR human factors·2025

Same author

Leveraging large language models for automated depression screening.

PLOS digital health·2025

Same author

The Impact of ChatGPT Exposure on User Interactions With a Motivational Interviewing Chatbot: Quasi-Experimental Study.

JMIR formative research·2025

Same author

Screening for Depression Using Natural Language Processing: Literature Review.

Interactive journal of medical research·2024

Same author

A Gender-Informed Smoking Cessation App for Women: Protocol for an Acceptability and Feasibility Study.

JMIR research protocols·2024

Search research articles

Related Experiment Video

Updated: Aug 5, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Predicting Generalized Anxiety Disorder From Impromptu Speech Transcripts Using Context-Aware Transformer-Based

Bazen Gashaw Teferra¹, Jonathan Rose^1,2

¹The Edward S Rogers Sr Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada.

JMIR Mental Health

|March 28, 2023

Summary

This summary is machine-generated.

Transformer models can detect generalized anxiety disorder from speech, outperforming traditional methods. Analyzing linguistic patterns in speech shows promise for future anxiety screening tools.

Keywords:

anxiety prediction generalized anxiety disorder impromptu speech linguistic features mental health mobile phone natural language processing neural networks transformer models

More Related Videos

Using the Threat Probability Task to Assess Anxiety and Fear During Uncertain and Certain Threat

Using the Threat Probability Task to Assess Anxiety and Fear During Uncertain and Certain Threat

Published on: September 12, 2014

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Aug 5, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Using the Threat Probability Task to Assess Anxiety and Fear During Uncertain and Certain Threat

Using the Threat Probability Task to Assess Anxiety and Fear During Uncertain and Certain Threat

Published on: September 12, 2014

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Natural Language Processing
Computational Linguistics
Psychiatry

Background:

Automatic detection of anxiety disorders from speech can serve as a valuable screening tool.
Previous research indicates a link between specific words in speech transcripts and anxiety severity.
Transformer-based neural networks excel at identifying linguistic patterns and contextual relationships in text.

Purpose of the Study:

To evaluate the efficacy of a transformer-based language model in screening for generalized anxiety disorder (GAD) using impromptu speech.
To compare the predictive performance of the transformer model against a baseline logistic regression model.

Main Methods:

2000 participants provided impromptu speech samples and completed the Generalized Anxiety Disorder 7-item (GAD-7) scale.
A transformer model was fine-tuned on speech transcripts and GAD-7 scores to predict GAD screening status.
Performance was measured by the area under the receiver operating characteristic curve (AUROC) and compared to a LIWC-based logistic regression model.

Main Results:

The transformer model achieved an AUROC of 0.64, outperforming the baseline LIWC model's AUROC of 0.58.
Context-dependent linguistic patterns, such as the use of "I" and the presence of silent pauses, significantly influenced predictions.
"I" usage predicted anxiety 88% of the time, while silent pauses predicted non-anxiety 80% of the time, depending on context.

Conclusions:

Transformer-based neural networks demonstrate superior predictive power for anxiety screening compared to traditional word-based methods.
The model's effectiveness is attributed to its ability to discern context-specific linguistic patterns.
These findings support the potential utility of transformer models in developing advanced anxiety screening systems.