相关实验视频
Updated: Jan 7, 2026
08:47
Oral Health Assessment by Lay Personnel for Older Adults
Published on: February 2, 2020
13.4K
大型语言模型在报告口腔健康问题和头癌的副作用方面的表现:一项比较研究
Jonas Rast1, Susanne Wiegand1, Jana Biermann2
1Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Schleswig-Holstein, Arnold-Heller-Straße 3, 24105, Kiel, Germany.
Journal of cancer research and clinical oncology
|December 20, 2025
概括
大型语言模型 (LLM) 对头癌 (HNC) 患者教育有希望,提供可理解的信息,误导风险低. 然而,它们的有限可操作性需要仔细整合到患者护理中.
科学领域:
- 医疗保健中的人工智能
- 数字健康干预措施 数字健康干预措施
- 患者教育 技术 技术
背景情况:
- 越来越多地依赖大型语言模型 (LLM) 来获取健康信息.
- 需要对特定患者群体的LLM绩效进行评估,例如头癌 (HNC) 幸存者.
- 口腔健康和副作用是接受治疗的HNC患者的关键问题.
研究的目的:
- 评估LLM对HNC患者口腔健康问题的响应的可靠性,质量,可理解性,可操作性,可读性和错误信息风险.
- 为了比较八个不同的LLMs在提供这些信息方面的表现.
- 为在HNC患者教育中安全有效地使用LLM提供信息.
主要方法:
- 确定了关于口腔健康和HNC副作用的常见问题.
- 已经向八个LLM提交了问题:ChatGPT-GPT-4-turbo,Gemini-2.5 Flash,微软Copilot,Perplexity,Chatsonic,Mistral,Meta AI-Llama 4,DeepSeek-R1. 这四个LLM都已经提交了问题.
- 通过使用DISCERN,修改后的DISCERN,PEMAT,Flesch-Reading-Ease-Score,错误信息得分和引用分析来评估答复.
主要成果:
- 在LLM中,在可靠性,可理解性,可操作性,可读性和单词数方面发现了统计学上显著的差异 (p < 0.001).
- 在LLM中,提供了可理解的信息 (PEMAT可理解性≥75.0),错误信息风险一般较低 (p=0.768).
- 然而,LLM提供了有限的具体指导 (PEMAT可操作性 ≤ 40) 并使用复杂的语言 (FRES ≤ 40.2).
结论:
- 由于其易理解性和低误传风险,LLM显示出HNC患者教育的潜力.
- 在LLM响应的可操作性缺陷突出需要谨慎.
- 建议仔细整合LLMs以支持,而不是取代现有的HNC患者教育策略.
相关概念视频
02:43Mouse Models of Cancer Study
6.3K
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
6.3K
01:21Cancer Survival Analysis
624
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
624