Scholarlink

Purpose <p>This study aims to compare the responses provided by commonly used artificial intelligence-based chatbots such as ChatGPT-3.5, ChatGPT-4o, Gemini 2.0 Flash, and DeepSeek-R1 about dental local anesthesia, sedation, and general anesthesia in terms of accuracy, reliability, and readability.</p> Methods <p>Sixty questions were created from the American Dental Association (ADA) and American Society of Anesthesiologists (ASA) guidelines. Thirty were patient questions, thirty professional questions. Each group contained ten open-ended, ten multiple-choice, and ten true/false questions. The questions were submitted to ChatGPT-3.5, ChatGPT-4o, DeepSeek-R1, and Gemini 2.0 Flash. Four blinded pediatric dentists evaluated the answers with a modified global quality scale. Clinical safety and risk analysis were evaluated using a 3-point Likert scale. Readability was measured by Flesch Reading Ease Score (FRE) and Flesch–Kincaid Grade Level (FKGL). The intraclass correlation coefficient (ICC) tested inter-rater reliability. Significance was set at <i>p</i> &lt; 0.05.</p> Results <p>DeepSeek-R1 demonstrated the highest overall accuracy and inter-rater agreement, providing the most accurate and reliability responses across all question types (<i>p</i> &lt; 0.001). It was followed by Gemini 2.0 Flash, ChatGPT-4o, and ChatGPT-3.5. In terms of readability, Gemini 2.0 Flash consistently produced the most accessible responses, while DeepSeek-R1 was significantly less readable (<i>p</i> = 0.012). GPT-3.5 showed variability by question type, with MCQs being easier to read than open-ended ones (<i>p</i> = 0.027). No significant readability differences were observed across question types for ChatGPT-4o, Gemini 2.0 Flash, or DeepSeek-R1 (<i>p</i> &gt; 0.05).</p> Conclusion <p>Chatbot performance depends on both question type and evaluation criteria. DeepSeek-R1 excelled in accuracy and quality. Gemini 2.0 Flash produced the clearest, patient-friendly responses. AI chatbots can support communication in dental anesthesia. Choosing the right model may improve education, assist clinical training, and guide professional decisions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluation of the accuracy, quality, and readability of large language models on local anesthesia and general anesthesia-sedation in dentistry

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月28日

查看全文
  • Semanur Özüdoğru,
  • Taibe Tokgöz Kaplan

摘要

Purpose

This study aims to compare the responses provided by commonly used artificial intelligence-based chatbots such as ChatGPT-3.5, ChatGPT-4o, Gemini 2.0 Flash, and DeepSeek-R1 about dental local anesthesia, sedation, and general anesthesia in terms of accuracy, reliability, and readability.

Methods

Sixty questions were created from the American Dental Association (ADA) and American Society of Anesthesiologists (ASA) guidelines. Thirty were patient questions, thirty professional questions. Each group contained ten open-ended, ten multiple-choice, and ten true/false questions. The questions were submitted to ChatGPT-3.5, ChatGPT-4o, DeepSeek-R1, and Gemini 2.0 Flash. Four blinded pediatric dentists evaluated the answers with a modified global quality scale. Clinical safety and risk analysis were evaluated using a 3-point Likert scale. Readability was measured by Flesch Reading Ease Score (FRE) and Flesch–Kincaid Grade Level (FKGL). The intraclass correlation coefficient (ICC) tested inter-rater reliability. Significance was set at p < 0.05.

Results

DeepSeek-R1 demonstrated the highest overall accuracy and inter-rater agreement, providing the most accurate and reliability responses across all question types (p < 0.001). It was followed by Gemini 2.0 Flash, ChatGPT-4o, and ChatGPT-3.5. In terms of readability, Gemini 2.0 Flash consistently produced the most accessible responses, while DeepSeek-R1 was significantly less readable (p = 0.012). GPT-3.5 showed variability by question type, with MCQs being easier to read than open-ended ones (p = 0.027). No significant readability differences were observed across question types for ChatGPT-4o, Gemini 2.0 Flash, or DeepSeek-R1 (p > 0.05).

Conclusion

Chatbot performance depends on both question type and evaluation criteria. DeepSeek-R1 excelled in accuracy and quality. Gemini 2.0 Flash produced the clearest, patient-friendly responses. AI chatbots can support communication in dental anesthesia. Choosing the right model may improve education, assist clinical training, and guide professional decisions.