What question did this study set out to answer?

This research aims to assess the performance of large language models in endodontic decision-making.

November 21, 2025Australian Endodontic JournalOpen Access

Clinical Relevance of Large Language Models in Endodontics: Diagnostic Appropriateness Based on 50 Simulated Case Scenarios

View Full Paper

Ask AI

Bookmark

Authors

BKBüşra Karaca YÇYunus Emre Çakmak DEDamla ErkalBurdur Mehmet Akif Ersoy Üniversitesi

Discussion

Member takes

Implication

Comparative analysis of diagnostic accuracy for endodontic treatment in simulated cases using multiple language models, indicating variability in performance.

Key Points

This research aims to assess the performance of large language models in endodontic decision-making.
Developed fifty clinical scenarios for evaluation.
Compared six large language models: ChatGPT‐4o, ChatGPT‐3.5, Claude 4, Copilot, DeepSeek‐V3, Gemini 2.5.
Scored responses by two specialists as appropriate or inappropriate.
Utilized repeated measures ANOVA and chi-square tests for statistical analysis.
Claude demonstrated the highest accuracy at 76%.
ChatGPT‐3.5 recorded the lowest accuracy at 40%.
Significant differences in model performance were observed (p < 0.05).
Performance was better on straightforward cases compared to complex scenarios.

Cite This Study

Karaca et al. (2025) studied this question.

synapsesocial.com/papers/6924e3ffc0ce034ddc34f58f https://doi.org/10.1111/aej.70040

View Full Paper

Ask AI

Bookmark

Implication

Comparative analysis of diagnostic accuracy for endodontic treatment in simulated cases using multiple language models, indicating variability in performance.

Clinical Relevance of Large Language Models in Endodontics: Diagnostic Appropriateness Based on 50 Simulated Case Scenarios

Discussion

Member takes

Implication

Key Points

Cite This Study

Clinical Relevance of Large Language Models in Endodontics: Diagnostic Appropriateness Based on 50 Simulated Case Scenarios

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider