Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 28, 2025BioengineeringOpen Access

Performance of ChatGPT-4 as an Auxiliary Tool: Evaluation of Accuracy and Repeatability on Orthodontic Radiology Questions

View Full Paper
Ask AI
Bookmark
Share

Authors

MMMercedes Morales MorilloNFNerea Iturralde FernándezLCLuis Daniel Pellicer Castillo

Discussion

Loading...

Member takes

Overview

Evaluation reveals ChatGPT-4's limited accuracy yet substantial inter-rater agreement in orthodontic radiology, indicating its potential role in education.

Key Points

  • Strict accuracy was 34.1%, demonstrating limited correctness despite substantial variability across questions.
  • Experts graded responses on a 3-point scale, achieving a high inter-rater agreement of 93.8%, suggesting reliable grading.
  • Mean partial-credit score was 1.09 out of 2.00, highlighting some level of correctness in the responses.
  • Findings suggest ChatGPT-4 could support educational efforts in dentistry while underlining its limitations in accuracy.

Cite This Study

Morillo et al. (2025) studied this question.

synapsesocial.com/papers/68d9052141e1c178a14f4feehttps://doi.org/10.3390/bioengineering12101031
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 3.5 and 4.0 in Oral Medicine and Radiology: A Comparative Query-Based Cross-sectional Study2025 · 4 citations
  2. 2How reliable is the artificial intelligence product large language model ChatGPT in orthodontics?2024 · 39 citations
  3. 3Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations2023 · 481 citations
  4. 4ChatGPT: A Useful Tool for Medical Students in Radiology Education?2025
  5. 5Assessing the Accuracy and Completeness of AI-Generated Dental Responses: An Evaluation of the Chat-GPT Model2025 · 9 citations