Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 10, 2025MedicinaOpen Access

Diagnostic Performance of ChatGPT-4o in Analyzing Oral Mucosal Lesions: A Comparative Study with Experts

View Full Paper
Ask AI
Bookmark
Share

Authors

LVLuigi Angelo VairaJLJérôme R. LechienAMAntonino Maniaci

Discussion

Loading...

Member takes

Overview

Pilot study assesses diagnostic accuracy of chatgpt-4o in analyzing oral mucosal lesions, indicating strong outcomes.

Key Points

  • ChatGPT-4o achieved an 85% correct diagnosis rate, demonstrating high diagnostic accuracy in oral mucosal lesion analysis.
  • Sensitivity and specificity were notably high at 91.7% and 100%, respectively, indicating strong performance compared to experts.
  • The study utilized a panel of five clinicians to establish reference diagnoses, supporting the validity of the AI's results.
  • With a false-negative rate of 8.3% for malignant lesions, specialist oversight remains essential despite strong AI performance.

Cite This Study

Vaira et al. (2025) studied this question.

synapsesocial.com/papers/68c23e02b210217d647904bdhttps://doi.org/10.3390/medicina61081379
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Evaluating ChatGPT's Diagnostic Accuracy in Oral Mucosal Lesions: A Comparative Study with a Maxillofacial Surgeon2025
  2. 2ChatGPT-4o Proves Effective in Accurately Diagnosing Dermoscopic Images of Benign and Malignant Skin Conditions2025
  3. 3Diagnostic Accuracy of ChatGPT Model 5.1 in the Optical Characterization of Colorectal Lesions2026
  4. 4Evaluating ChatGPT 3.5 and 4.0 in Oral Medicine and Radiology: A Comparative Query-Based Cross-sectional Study2025 · 4 citations
  5. 5Accuracy of ChatGPT‐4 Plus in Providing Information on Oral Cancer Management2025 · 2 citations