Related Experiment Video
Updated: Jan 7, 2026
07:32
Author Spotlight: 3D Movement Assessment of Maxillary Posterior Teeth in Clear Aligner Treatment
Published on: February 23, 2024
1.7K
Comparing large language models and search engine responses to common orthodontic questions
1School of Nursing, Peking University, Beijing, China.
Plos One
|January 2, 2026
Summary
Large Language Models (LLMs) provide superior orthodontic patient education compared to search engines, demonstrating higher quality, empathy, and readability. This suggests LLMs can aid in patient self-management.
Area of Science:
- Artificial Intelligence in Healthcare
- Digital Health
- Orthodontic Patient Education
Background:
- Large Language Models (LLMs) show promise for patient education and self-management.
- LLM performance in answering orthodontic questions is largely unexplored.
Purpose of the Study:
- To compare LLM and search engine responses for orthodontic questions.
- Evaluate quality, empathy, readability, and patient satisfaction.
Main Methods:
- 45 common orthodontic questions across 6 categories were used.
- 5 LLMs and 3 search engines were queried on December 22, 2024.
- Expert ratings on Likert scales assessed response quality, empathy, readability, and satisfaction.
Main Results:
- LLMs significantly outperformed search engines in quality (4.00 vs. 3.50), empathy (3.75 vs. 3.50), readability (4.00 vs. 3.75), and satisfaction (8.00 vs. 7.25).
- LLM responses were superior in therapeutic outcomes, appliance selection, and cost categories.
Conclusions:
- LLMs, especially GPT-4o, demonstrated better performance than search engines.
- LLMs show potential as supplementary tools for orthodontic patient education and self-management.
