确保安全和信任:分析医学中大型语言模型的风险
Yifan Yang1,2, Qiao Jin1, Robert Leaman1
1Division of Intramural Research, National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, MD 20894, USA.
ArXiv
|October 1, 2025
概括
大型语言模型 (LLM) 在医疗保健中显示出潜力,但存在重大安全差距. 目前的模型在医疗基准上表现不佳,需要人类监督和人工智能安全护,以获得可靠的医疗人工智能.
科学领域:
- 人工智能的人工智能
- 医疗信息学 医疗信息学
- 医疗保健技术 技术 医疗保健 技术
背景情况:
- 大型语言模型 (LLM) 展示了先进的能力,引发了人们对其在医疗保健中的应用的兴趣.
- 然而,缺乏在医疗环境中对LLM相关风险的系统性描述.
- 确保安全和值得信赖的AI对于临床采用至关重要.
研究的目的:
- 系统地描述LLM在医疗应用中的风险.
- 提出一个安全可信的医疗人工智能框架,包括五个关键原则:真实性,弹性,公平性,稳定性和隐私.
- 引入MedGuard基准来评估医疗保健中的LLM绩效.
主要方法:
- 为医疗人工智能安全制定综合框架.
- 创建了MedGuard基准,包括1000个经过专家验证的医疗问题.
- 根据MedGuard基准,对11种常用的LLM进行评估.
主要成果:
- 目前的LLM通常在大多数MedGuard基准中表现不佳,即使有安全调整.
- 在医疗任务中,LLM的表现明显落后于人类医生的表现.
- 目前的LLM与安全临床部署的要求之间存在着显著的安全差距.
结论:
- 尽管LLM具有潜力,但严重的安全差距阻碍了它们在医疗保健中的广泛采用.
- 人类监督和强大的AI安全护对于减轻风险至关重要.
- 需要进一步的研究和开发,以提高LLM在医疗应用中的安全性和可靠性.
相关概念视频
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
407
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,...
407
01:27Language and Cognition
715
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
715
02:07Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
02:07Improving Translational Accuracy
3.5K
3.5K
01:15Methods of Documentation VI: Case Management Model
860
The case management model is a multidisciplinary approach that involves healthcare professionals from diverse disciplines, such as physicians, nurses, therapists, social workers, and pharmacists, working collaboratively to address the various needs of patients. Each healthcare professional brings unique expertise and perspectives, contributing to a more comprehensive understanding of the patient's condition and tailoring treatment plans accordingly.
For example, a patient with a chronic...
For example, a patient with a chronic...
860
01:30Guidelines for Nursing Documentation I
1.8K
Quality documentation and reporting share essential characteristics that ensure they are practical and valuable resources for those who use them. These characteristics are:
Factual:
The following points emphasize the significance of upholding accurate and unbiased documentation in healthcare.
Factual:
The following points emphasize the significance of upholding accurate and unbiased documentation in healthcare.
1.8K