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

Genetic Lingo

Genetic Lingo

You might also read

Related Articles

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

Sort by

Same author

Tumor probability mapping of fluorescence intensity during image-guided surgery of head and neck cancer.

Scientific reports·2026

Same author

Mucoacinar Carcinoma of the Parotid Gland.

Head and neck pathology·2026

Same author

Treatment of Friction Injury Using Enzymatic Debridement and Autologous Skin Cell Suspension.

Journal of burn care & research : official publication of the American Burn Association·2026

Same author

Survivorship, complications, and outcomes of custom glenoid implants in reverse total shoulder arthroplasty: a systematic review.

JSES reviews, reports, and techniques·2025

Same author

Esophageal Perforation Following Explosive Injury: A Case Report.

Journal of special operations medicine : a peer reviewed journal for SOF medical professionals·2025

Same author

Impact of Donor and Host Age on Systemic Cell Therapy to Treat Age-Related Macular Degeneration.

Cells·2025

Same journal

Osteoradionecrosis of the Scalp: A Case Series Highlighting Clinical Challenges and Literature Gaps.

OTO open·2026

Same journal

Voice Outcomes of Patients Intubated for Critical COVID Illness: A Multicenter Study.

OTO open·2026

Same journal

Development and Evaluation of the Adenoid/Nasopharynx Area Ratio on Lateral Cephalograms: Correlation With Nasal Endoscopy.

OTO open·2026

Same journal

Comprehensive Analysis and Genetic Insights Into GJB2 c.35delG Mutation-Associated Non-Syndromic Hearing Loss in Morocco.

OTO open·2026

Same journal

The Use of Contralateral AEA-Pedicled Septal Flap Combined With HBF for Complex Skull Base Defects.

OTO open·2026

Same journal

Aging and Hearing with Vestibular Schwannoma Beyond Presbycusis: A Large Cross-Sectional Audiometric and Volumetric Study.

OTO open·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 5, 2026

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Published on: March 18, 2020

Domain-Specific Customization for Language Models in Otolaryngology: The ENT GPT Assistant.

Brenton T Bicknell¹, Nicholas J Rivers², Adam Skelton¹

¹UAB Heersink School of Medicine University of Alabama at Birmingham Birmingham Alabama USA.

|May 7, 2025

Summary

This summary is machine-generated.

Domain-specific customization enhances large language models (LLMs) for otolaryngology. The ENT GPT Assistant (E-GPT-A) outperformed other AI models in otolaryngology assessments.

Keywords:

artificial intelligence comprehensive otolaryngology machine learning natural language processing

More Related Videos

A Heterotopic Mouse Model for Studying Laryngeal Transplantation

A Heterotopic Mouse Model for Studying Laryngeal Transplantation

Published on: January 13, 2023

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: May 5, 2026

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Published on: March 18, 2020

A Heterotopic Mouse Model for Studying Laryngeal Transplantation

A Heterotopic Mouse Model for Studying Laryngeal Transplantation

Published on: January 13, 2023

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:

Artificial Intelligence
Medical Informatics
Otolaryngology

Background:

Large language models (LLMs) show promise in various fields.
Domain-specific customization is a potential method to improve LLM performance in specialized areas.
Otolaryngology (ENT) requires accurate and efficient information processing.

Purpose of the Study:

To develop and evaluate the effectiveness of a domain-specific customized LLM for otolaryngology.
To assess the performance of the ENT GPT Assistant (E-GPT-A) compared to general LLMs.

Main Methods:

A specialized LLM, E-GPT-A, was created using targeted instructions for otolaryngology.
Performance was evaluated using 240 clinical-vignette multiple-choice questions (MCQs) from otolaryngology resources.
E-GPT-A's accuracy was compared against GPT-3.5, GPT-4, Claude 2.0, and Claude 2.1.

Main Results:

E-GPT-A achieved 74.6% overall accuracy, surpassing GPT-3.5 (60.4%), Claude 2.0 (61.7%), Claude 2.1 (60.8%), and GPT-4 (68.3%).
Highest accuracy was observed in allergy/rhinology (85.0%) and laryngology (82.5%).
Accuracy decreased with increased question difficulty and was lower in pediatrics (62.5%) and facial plastics (67.5%).

Conclusions:

Domain-specific customization of LLMs, like E-GPT-A, shows potential benefits for otolaryngology.
Further development, updates, and real-world validation are necessary to fully establish LLM capabilities in this field.