Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 1, 2026Journal of Indian Academy of Oral Medicine and RadiologyOpen Access

Performance Comparison of Artificial Intelligence Chatbots in Addressing Oral Lesion Queries: An In Silico Cross-Sectional Study

View Full Paper
Ask AI
Bookmark
Share

Authors

VBV BalajeePPP Roland PrethipaADAyesh Das

Discussion

Loading...

Member takes

Overview

Cross-sectional study evaluates AI chatbots' effectiveness in addressing oral lesion inquiries, indicating varying reliability.

Key Points

  • Evaluate and compare the performance of AI chatbots in answering queries about oral lesions.
  • Curated twenty patient-centered questions from reputable health sources.
  • Entered questions into three AI chatbots under standardized conditions.
  • Rated responses using a five-point Likert scale by calibrated observers.
  • Analyzed readability with Flesch Reading Ease and Flesch–Kincaid Grade Level indices.
  • Google Gemini and ChatGPT outperformed Microsoft Copilot in accuracy and safety.
  • Significant differences in accuracy (P = 0.022) and safety (P < 0.001) were noted.
  • ChatGPT had the best readability (FKGL = 6.58, FRE = 59.64).
  • Inter-rater agreement was highest for Microsoft Copilot (κ ≈ 0.8).

Cite This Study

Balajee et al. (2026) studied this question.

synapsesocial.com/papers/69ccb5f716edfba7beb87b5chttps://doi.org/10.4103/jiaomr.jiaomr_380_25
View Full Paper
Ask AI
Bookmark
Share