在ChatGPT生成的医疗内容中,虚构和不准确的引用率很高
Mehul Bhattacharyya1, Valerie M Miller2, Debjani Bhattacharyya3
1Clinical Research, Miller Scientific, Johnson City, USA.
大多数由人工智能 (AI) 工具 (如ChatGPT) 为医疗信息生成的引用都是不准确的或伪造的. 总是通过可信来源验证人工智能生成的医疗内容.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
背景情况:
- 像ChatGPT这样的大型语言模型 (LLM) 提供了可访问的医疗信息.
- 人工智能产生的医疗内容的准确性和引用仍然存在担忧.
研究的目的:
- 调查ChatGPT生成的医疗文章中引用的真实性和准确性.
- 评估人工智能生成的医学文献的可靠性.
主要方法:
- 观察性研究分析了30个ChatGPT-3.5生成的医学论文.
- 使用Medline,谷歌学者和DOAJ验证了115个参考文献.
- 对个别参考组件的准确性进行评估.
主要成果:
- 47%的引用是捏造的,46%是真实的但不准确的,只有7%是真实的和准确的.
- 错误的PMID数字 (93%) 和出版细节 (卷,页面,年份) 是常见的错误.
- 快速变化影响了制造率,但准确的引用始终很低.
结论:
- 建议在使用ChatGPT来获取医疗信息时谨慎使用,这是由于普遍存在的参考不准确性.
- 个人应该与可靠来源交叉引用人工智能生成的医疗内容.
- 不鼓励过度依赖人工智能生成的医学文献.
更多相关视频
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
相关概念视频
Healthcare Associated Infections I: Iatrogenic, Exogenic and Endogenic
HAIs significantly increase the cost of health care. Extended stays in healthcare institutions, increased disability, increased costs of medications, including specialized antibiotics, and prolonged recovery times add to the patient's expenses and the healthcare institution and funding bodies.
Errors occurring during blood pressure monitoring
Several factors...
The Availability Heuristic
Health Information Technology and Healthcare Information System
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Integrated Healthcare System
