Related Experiment Video
Updated: May 16, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
745
Can Artificial Intelligence Language Models Effectively Address Dental Trauma Questions?
Hasibe Elif Kuru1, Aslı Aşık2, Doğukan Mert Demir3
1Faculty of Dentistry, Department of Pediatric Dentistry, Uşak University, Uşak, Turkey.
Summary
Large language models (LLMs) show potential for dental trauma education, but their accuracy varies. ChatGPT 3.5 performed best, while Gemini struggled, highlighting the need for careful integration of AI in healthcare education.
Area of Science:
- Artificial Intelligence in Healthcare
- Dental Traumatology Education
- Natural Language Processing Applications
Background:
- Artificial intelligence (AI) chatbots, or large language models (LLMs), are increasingly adopted as educational resources in healthcare settings.
- The application of LLMs for emergency dental trauma education is growing, necessitating an evaluation of their reliability and accuracy.
Purpose of the Study:
- To compare the reliability and accuracy of different large language models (LLMs) when responding to queries concerning dental trauma.
- To assess the performance of five distinct LLMs: ChatGPT 4, ChatGPT 3.5, Copilot Free, Copilot Pro, and Google Gemini.
Main Methods:
- A cross-sectional observational study involved posing 30 questions based on International Association of Dental Traumatology guidelines to five LLMs.
- Questions included multiple-choice, fill-in-the-blank, and dichotomous formats, administered over nine consecutive days.
- Responses were analyzed for correctness and consistency using statistical tests, with a significance level of p < 0.05.
Main Results:
- All LLMs demonstrated high repeatability in answering repeated questions.
- ChatGPT 3.5 achieved the highest success rate (76.7%), followed by Copilot Pro (73.3%), Copilot Free (70%), ChatGPT 4 (63.3%), and Gemini (46.7%).
- ChatGPT 3.5, ChatGPT 4, and Gemini performed significantly better on multiple-choice and fill-in-the-blank questions than dichotomous ones; Copilot models showed no significant difference across question types. Explanations and references from Copilot and Gemini were often inaccurate.
Conclusions:
- Large language models (LLMs) present potential as supplementary educational tools in dental traumatology.
- Variable accuracy and the inclusion of unreliable references necessitate cautious implementation strategies for LLMs in dental education.
- Further research is required to optimize the use of AI in clinical education.
Related Concept Videos
01:15Teeth
264
The formation of teeth, also known as odontogenesis, is a complex process that begins in utero, around the sixth week of embryonic development. There are three stages to this process: the bud stage, the cap stage, and the bell stage.
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin...
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin...
264
01:08The Availability Heuristic
5.9K
A heuristic is a general problem-solving framework (Tversky & Kahneman, 1974). You can think of these as mental shortcuts that are used to solve problems. Different types of heuristics are used in different types of situations, and the impulse to use a heuristic occurs when one of five conditions is met (Pratkanis, 1989):
5.9K