聊天GPT产生的关于干预放射科医生管理的疾病信息的质量
Ruairidh Read1, Matthew Lukies2
1Box Hill Hospital, Eastern Health, Melbourne, Victoria, Australia.
Journal of medical imaging and radiation oncology
|August 9, 2025
概括
像ChatGPT这样的大型语言模型 (LLM) 提供健康信息,但缺乏来源透明度和治疗风险和益处的细节. 干预放射学 (IR) 专业人员应指导患者使用LLM生成的内容.
科学领域:
- 人工智能在医学中的应用
- 医疗信息传播 医疗信息传播
背景情况:
- 新兴的人工智能驱动的搜索引擎和LLM提供可访问的健康信息.
- 人工智能产生的健康内容的准确性和可靠性仍然不确定.
- 干预放射学 (IR) 经常管理需要人工智能生成的治疗信息的情况.
研究的目的:
- 评估ChatGPT生成的关于常见干预放射学 (IR) 条件的治疗方法信息的质量.
- 将人工智能生成的医疗信息与已建立的证据基础进行比较.
主要方法:
- 对于六个IR管理的条件,ChatGPT被查询为"最佳治疗".
- 通过使用DISCERN仪器评估了输出.
- 人工智能生成的信息与当前的证据基础进行了比较.
主要成果:
- 聊天GPT的平均得分 (1.3) 比参考文章 (3.8) 显著低.
- 缺点包括缺乏来源透明度,以及治疗风险,益处和机制的细节不足.
- 优势包括信息的公正呈现.
结论:
- 在患者获取医疗信息方面,LLM代表了重大变化.
- 了解LLM的优缺点对于干预放射科医生 (IR) 来说至关重要.
- 量身定制的患者沟通和与IR进行咨询对于导航人工智能生成的健康内容至关重要.
相关概念视频
Interpreting Run Charts
2.3K
Run charts, essentially line graphs plotted over time, serve as fundamental yet effective tools for process analysis. They chronicle data sequentially, facilitating the identification of trends, shifts, or cyclical movements. This graphical representation is instrumental in determining whether a process is stable or exhibits signs of potential instability indicative of special cause variation. In the healthcare domain, run charts depict infection rates over time, enabling hospitals to monitor...
2.3K
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
174
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
174


