医学中的忠实人工智能:用大型语言模型和超越的系统审查
Qianqian Xie1, Edward J Schenck2, He S Yang3
1Weill Cornell Medicine.
Research square
|December 18, 2023
概括
本文审查了人工智能 (AI) 在医学中的忠实性,重点关注大型语言模型 (LLM). 它强调了在医疗保健中确保准确可靠的人工智能的挑战和机会.
科学领域:
- 医疗人工智能 医疗人工智能
- 自然语言处理自然语言处理.
- 医疗保健信息学 医疗保健信息学
背景情况:
- 人工智能 (AI),特别是大型语言模型 (LLM),在医学上看起来很有前途,但由于产生事实上不正确的信息而面临风险.
- 确保人工智能输出的忠实性对于患者安全和伦理医疗应用至关重要.
- 现有的医疗保健人工智能研究往往忽视了事实准确性的具体挑战.
研究的目的:
- 综合审查医疗保健人工智能的忠实性问题.
- 分析不忠诚的人工智能输出的原因,当前的评估指标和缓解技术.
主要方法:
- 使用PRISMA方法的系统审查.
- 来自5个主要数据库 (PubMed,Scopus,IEEE Xplore,ACM数字图书馆,谷歌学者) 的5061个记录,发表于2018年1月 - 2023年3月.
- 包括40篇相关文章,重点关注生成医学AI事实.
主要成果:
- 审查了在生成医学AI中优化和评估事实性的最新进展.
- 涵盖基于知识的LLM,文本到文本生成,多模式到文本生成和自动医疗事实核查.
- 确定了数据资源,骨干模型,缓解方法和评估指标方面的挑战.
结论:
- 进一步的研究对于提高AI在医疗应用中的可靠性和事实性至关重要.
- 解决数据局限性和开发标准化评估指标是关键的下一步.
- 开发忠实的人工智能是实现人工智能在医疗保健中安全和道德整合的关键.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
231
07:50A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
15.9K
相关概念视频
Issues And Trends In Healthcare Delivery System
5.6K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.6K
Improving Translational Accuracy
2.6K
2.6K
