⚡ Quick Summary
This study evaluated the diagnostic performance of three prominent AI-powered large language models (LLMs)—ChatGPT, Copilot, and Gemini—in diagnosing oral lesions and periodontal conditions. The results indicated that ChatGPT outperformed the other models with a score of 4.846, highlighting its potential as a reliable AI assistant in clinical dentistry.
🔍 Key Details
- 📊 Dataset: 385 cases with definite diagnoses from Taibah University, Saudi Arabia
- 🧩 Evaluation Criteria: 8 criteria including diagnostic concordance and time efficiency
- ⚙️ Technology: AI models evaluated: ChatGPT, Copilot, Gemini
- 🏆 Performance: ChatGPT: 4.846, Copilot: 4.433, Gemini: 4.234
- 📈 Statistical Analysis: Included Friedman tests and Cronbach’s alpha for reliability
🔑 Key Takeaways
- 🤖 ChatGPT demonstrated superior diagnostic performance compared to Copilot and Gemini.
- 📊 Statistical significance was found across all evaluation criteria (P<0.001).
- 🧩 Internal consistency of the models was excellent (Cronbach alpha: 0.801-0.911).
- 💡 AI assistants show promise for integration into clinical practice for oral and periodontal diagnosis.
- 🌍 Study conducted at the College of Dentistry, Taibah University.
- 📈 Comprehensive analysis supports the reliability of AI in clinical decision-making.
📚 Background
The integration of artificial intelligence in healthcare has been a transformative force, particularly in diagnostics. In dentistry, accurate diagnosis of oral lesions and periodontal conditions is crucial for effective treatment. This study aims to explore the capabilities of AI-powered LLMs in enhancing diagnostic accuracy and efficiency in dental practice.
🗒️ Study
Conducted as a retrograde study, this research involved a comprehensive evaluation of 385 clinical cases with confirmed diagnoses. Each AI model was presented with clinical and radiographic images, and their diagnostic performance was assessed using a 5-point Likert scale across various criteria, including clarity of explanation and reliability.
📈 Results
The findings revealed that ChatGPT achieved the highest overall score of 4.846±0.075, significantly outperforming both Copilot (4.433±0.163) and Gemini (4.234±0.088). The statistical analysis confirmed significant differences in performance across all criteria, indicating that ChatGPT is a robust tool for dental diagnostics.
🌍 Impact and Implications
The results of this study suggest that AI-powered LLMs, particularly ChatGPT, have the potential to revolutionize the field of dentistry. By providing reliable and efficient diagnostic support, these technologies can enhance clinical decision-making, ultimately leading to improved patient outcomes. The integration of AI in dental practice could pave the way for more precise and timely interventions.
🔮 Conclusion
This study highlights the significant potential of AI assistants in the realm of oral and periodontal diagnosis. With ChatGPT demonstrating superior performance, there is a strong case for its integration into clinical practice. As AI continues to evolve, its role in enhancing diagnostic accuracy and efficiency in dentistry will likely expand, offering exciting possibilities for the future of dental care.
💬 Your comments
What are your thoughts on the use of AI in dentistry? Do you believe it can truly enhance diagnostic accuracy? Let’s discuss! 💬 Leave your comments below or connect with us on social media:
AI-Powered Clinical Decision Support in Dentistry: Comparative Evaluation of Large Language Models for Oral Medicine and Periodontal Diagnosis.
Abstract
BACKGROUND This study evaluates the diagnostic performance of 3 prominent artificial intelligence (AI)-powered large language models (LLMs) – ChatGPT, Copilot, and Gemini – as AI assistants for the diagnosis of oral lesions and periodontal conditions using comprehensive statistical analysis. MATERIAL AND METHODS A retrograde study was conducted on 385 cases with definite diagnoses from the College of Dentistry, Taibah University, Saudi Arabia. Clinical and radiographic images were presented to each AI model, and the diagnostic performance of the LLMs was evaluated using a 5-point Likert scale across 8 criteria: diagnostic concordance, time efficiency, ease of use, clarity of explanation, comprehensiveness, ability to answer questions, reliability, and diagnostic range. Statistical analysis included descriptive statistics with 95% confidence intervals, Friedman tests, post-hoc pairwise comparisons, correlation analysis, effect size calculations, and reliability assessment using Cronbach’s alpha. RESULTS ChatGPT demonstrated superior performance with an overall score of 4.846±0.075, followed by Copilot (4.433±0.163) and Gemini (4.234±0.088). Friedman tests revealed statistically significant differences across all evaluation criteria (P<0.001). Post-hoc analyses showed ChatGPT significantly outperformed both Gemini and Copilot in all criteria. Internal consistency was excellent for all systems (Cronbach alpha: 0.801-0.911). CONCLUSIONS The LLMs, particularly ChatGPT, demonstrate significant potential as reliable AI assistants for oral and periodontal diagnosis. The comprehensive statistical analysis confirms the superior performance of ChatGPT across multiple evaluation dimensions, supporting its potential integration into clinical practice.
Author: [‘Meer RM’, ‘Alqarni A’, ‘Akily BM’, ‘Zaki H’, ‘Fayad MI’, ‘AbdElaziz MHH’, ‘Elboraey MO’]
Journal: Med Sci Monit
Citation: Meer RM, et al. AI-Powered Clinical Decision Support in Dentistry: Comparative Evaluation of Large Language Models for Oral Medicine and Periodontal Diagnosis. AI-Powered Clinical Decision Support in Dentistry: Comparative Evaluation of Large Language Models for Oral Medicine and Periodontal Diagnosis. 2026; 32:e951721. doi: 10.12659/MSM.951721