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

Search research articles

Related Experiment Video

Updated: May 14, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

Diagnostic Performance of a Large Language Model (ChatGPT-4o) in Chronic Rhinosinusitis CT Scan Interpretation.

Mohammed Sulaiman Alsayyari¹, Hassan Alshurafa¹, Waleed Abdelkader²

¹College of Medicine King Saud University Riyadh Saudi Arabia.

Laryngoscope Investigative Otolaryngology

|May 13, 2026

Summary

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

Ear-nose-throat manifestations of granulomatosis with polyangiitis and eosinophilic granulomatosis with polyangiitis: a cross-sectional study.

Rheumatology international·2026

Same author

Diagnostic Performance of Artificial Intelligence in Salivary Gland Tumors Using Ultrasound Imaging: A Systematic Review.

Ear, nose, & throat journal·2026

Same author

Acute exacerbation of chronic rhinosinusitis: clinical and microbiological perspectives from a Saudi tertiary care center.

Annals of Saudi medicine·2026

Same author

Follicular Thyroid Carcinoma Metastasis to the Retromolar Trigone: A Case Report.

Cureus·2026

Same author

Rhinophyma: a systematic review and meta-analysis of its epidemiology, associations, and treatment outcomes.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2026

Same author

Vertical Banded Gastroplasty Revisions: A Single-Center Experience.

Cureus·2025

Large language models (LLMs) show inconsistent performance in interpreting sinus CT scans for chronic rhinosinusitis (CRS). Radiologists remain essential for accurate diagnosis, and LLM use in medical imaging requires caution.

Area of Science:

Medical Imaging
Artificial Intelligence in Medicine
Radiology

Background:

Large language models (LLMs) like ChatGPT are increasingly used for clinical decision support.
Their diagnostic performance in medical imaging, specifically sinus CT scans for chronic rhinosinusitis (CRS), is largely untested.
This study prospectively evaluates ChatGPT's interpretation capabilities against radiologist assessments.

Purpose of the Study:

To prospectively evaluate the diagnostic performance of ChatGPT-4o in interpreting sinus CT scans for CRS.
To compare ChatGPT's interpretations with those of a board-certified radiologist.
To assess the repeatability and inter-rater agreement of ChatGPT's interpretations.

Main Methods:

A prospective cohort study involving 102 coronal sinus CT scans.

Keywords:

ChatGPT artificial intelligence computed tomography rhinology rhinosinusitis

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Related Experiment Videos

Last Updated: May 14, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Scans were interpreted by both a radiologist and ChatGPT-4o, with ChatGPT interpretations performed twice for repeatability.

Both raters assessed 11 anatomical features and generated Lund-Mackay scores; diagnostic performance and agreement were statistically analyzed.

Main Results:

ChatGPT showed variable sensitivity (0.00-0.89) and specificity (0.26-0.95) across anatomical features.
High sensitivity was noted for mucosal thickening and sinus expansion; strong agreement with radiologists was found for lamina papyracea and anterior ethmoid artery.
Performance was poor for air-fluid levels and bone thinning, with limited repeatability and weak correlation for Lund-Mackay scores.

Conclusions:

ChatGPT demonstrates partial capability in identifying specific sinus CT findings but lacks overall diagnostic consistency.
Human radiologists are essential for accurate interpretation of sinus CT scans.
Clinical application of LLMs in medical imaging should be approached with caution due to current limitations.