A cross-sectional comparative study: ChatGPT 3.5 versus diverse levels of medical experts in the diagnosis of ENT diseases.

Eur Arch Otorhinolaryngol

Department of Otolaryngology-Head and Neck Surgery, Hotel Dieu de France Hospital, Saint Joseph University, Alfred Naccache Boulevard, Ashrafieh, PO Box: 166830, Beirut, Lebanon.

Published: May 2024

Purpose: With recent advances in artificial intelligence (AI), it has become crucial to thoroughly evaluate its applicability in healthcare. This study aimed to assess the accuracy of ChatGPT in diagnosing ear, nose, and throat (ENT) pathology, and comparing its performance to that of medical experts.

Methods: We conducted a cross-sectional comparative study where 32 ENT cases were presented to ChatGPT 3.5, ENT physicians, ENT residents, family medicine (FM) specialists, second-year medical students (Med2), and third-year medical students (Med3). Each participant provided three differential diagnoses. The study analyzed diagnostic accuracy rates and inter-rater agreement within and between participant groups and ChatGPT.

Results: The accuracy rate of ChatGPT was 70.8%, being not significantly different from ENT physicians or ENT residents. However, a significant difference in correctness rate existed between ChatGPT and FM specialists (49.8%, p < 0.001), and between ChatGPT and medical students (Med2 47.5%, p < 0.001; Med3 47%, p < 0.001). Inter-rater agreement for the differential diagnosis between ChatGPT and each participant group was either poor or fair. In 68.75% of cases, ChatGPT failed to mention the most critical diagnosis.

Conclusions: ChatGPT demonstrated accuracy comparable to that of ENT physicians and ENT residents in diagnosing ENT pathology, outperforming FM specialists, Med2 and Med3. However, it showed limitations in identifying the most critical diagnosis.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00405-024-08509-zDOI Listing

Publication Analysis

Top Keywords

cross-sectional comparative
8
comparative study
8
ent physicians
8
physicians ent
8
ent residents
8
medical students
8
ent
7
chatgpt
5
study
4
study chatgpt
4

Similar Publications

Comparison of the Predictive Role of Spiritual Well-Being and Pain Intensity on Pain Catastrophizing in Acute and Chronic Pain.

Pain Manag Nurs

January 2025

Department of Nursing, Erciyes University, Faculty of Health Sciences, Kayseri, Turkey. Electronic address:

Aim: This study was conducted to compare the predictive effect of spiritual well-being and pain intensity on pain catastrophizing of individuals with acute and chronic pain.

Design: This research is a cross-sectional and comparative study.

Methods: The study included 116 individuals with chronic pain and 111 individuals with acute pain.

View Article and Find Full Text PDF

To explore the changes of atlantoaxial joint spaces and pharyngeal airway after combined orthodontic-orthognathic treatment in skeletal class Ⅲ patients with mandibular deviation. A total of 34 adult skeletal class Ⅲ patients (10 males and 24 females) with mandibular deviation who received combined orthodontic-orthognathic treatment at the Department of Orthodontics and the Department of Orthognathic Surgery in the Stomatological Hospital of Chongqing Medical University from August 2014 to October 2021 were retrospectively selected. The patients were 22 (5) years old (18-33 years).

View Article and Find Full Text PDF

Background And Purpose: Changes in perivascular fat density (PFD) and its association with inflammation have been topics of interest in both atherosclerotic and nonatherosclerotic vasculopathies. The objective of this study was to assess the PFD in patients with spontaneous internal carotid artery dissection (SICAD) or carotid atherosclerotic plaque, with and without intraplaque hemorrhage (IPH).

Materials And Methods: A cross-sectional retrospective bicentric analysis of 130 patients (30 with SICAD and 100 with carotid atherosclerotic plaque) who underwent CT angiography was performed.

View Article and Find Full Text PDF

How Do Clinicians Use Quotations in Goals of Care Notes?

Chest

January 2025

Division of General Internal Medicine, Section of Palliative Care and Medical Ethics, University of Pittsburgh, Pittsburgh, Pennsylvania; Palliative Research Center, University of Pittsburgh, Pittsburgh, Pennsylvania.

Background: Quoting patients in electronic medical record (EMR) notes is controversial. Quotations may be used to promote accuracy in documentation. However they also may be used to cast skepticism on patient speech.

View Article and Find Full Text PDF

Phenotypic Heterogeneity of ADTKD-MUC1 Diagnosed Using VNtyper, a Novel Genetic Technique.

Am J Kidney Dis

January 2025

Hereditary Kidney Diseases Laboratory, Inserm UMR 1163, Imagine Institute, Paris Cité University, Paris, France; Department of Genomic Medicine for Rare Diseases, Necker-Enfants Malades Hospital, Assistance publique, Hôpitaux de Paris (AP-HP), Paris, France. Electronic address:

Rationale & Objective: Molecular diagnosis of autosomal dominant tubulointerstitial kidney disease (ADTKD) due to variants in the MUC1 gene has long been challenging since variants lie in a large Variable Number of Tandem Repeat (VNTR) region, making identification impossible using standard short read techniques. Previously, we addressed this diagnostic limitation by developing a computational pipeline, named VNtyper, for easier reliable detection of MUC1 VNTR pathogenic variants from short read sequences. This led to unexpected diagnoses of ADTKD-MUC1 among patients with kidney disease referred for genetic testing, which we report here.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!