提炼大型语言模型,使患者与临床试验相匹配
Mauro Nievas1, Aditya Basu2, Yanshan Wang3
1Triomics Research, Triomics, Inc., San Francisco, CA 94105, United States.
概括
开源大型语言模型 (LLM) 在微调后的医疗保健患者试验匹配中显示出与专有LLM可比的性能. 这项研究为临床试验招聘提供了可访问,可重复的解决方案.
科学领域:
- 医疗保健中的人工智能
- 临床试验招聘 临床试验招聘
- 自然语言处理自然语言处理.
背景情况:
- 专有的大型语言模型 (LLM),如GPT-3.5和GPT-4,在医疗保健应用中显示出有前途.
- 开源的LLM (例如LLAMA) 在成本,隐私和可重复性方面提供了潜在的优势.
- 患者与试验的匹配是临床研究中一个关键但复杂的过程.
研究的目的:
- 系统地评估专有和开源的LLM在患者试验匹配方面的有效性.
- 为了比较不同LLM在对临床试验标准分析患者资格方面的表现.
- 调查微调对开源LLM在医疗保健环境中的表现的影响.
主要方法:
- 采用了多方面的评估框架,包括自动化和以人为中心的评估.
- 对每个LLM进行了错误分析,以确定性能限制.
- 使用GPT-4生成的合成数据集被用于在数据限制下微调开源LLM.
主要成果:
- 精心调整的开源LLM与GPT-3.5.5等专有模型实现了性能平价.
- 该研究证明了对有限的合成数据集进行微调的有效性.
- 开源的LLM在分析患者资格标准方面表现出显著的能力.
结论:
- 开源的LLM是医疗保健中患者试验匹配的可行和有前途的工具.
- 微调使开源模型能够克服与专有法学士相关的挑战.
- 该研究发布了注释数据集和微调的LLM (试验LLAMA),以促进进一步的研究和应用.
相关概念视频
01:16Clinical Trials
Clinical trials are prospective experimental studies conducted on humans to determine the safety and efficacy of treatments, drugs, diet methods, and medical devices. Using statistics in clinical trials enables researchers to derive reasonable and accurate conclusions from the collected data, allowing them to make wise decisions in uncertain situations. In medical research, statistical methods are crucial for preventing errors and bias.
There are four phases in a clinical trial. A phase one...
There are four phases in a clinical trial. A phase one...
01:11Clinical Trials: Overview
Clinical development focuses on how the drug will interact with the human body and encompasses four key phases of clinical trials, each serving a specific purpose in assessing the safety and effectiveness of new drugs. These phases overlap and build upon one another. Phase I involves a small group of healthy volunteers (typically 20-80 individuals) or, in cases where significant toxicity is expected, patients with the targeted disease, such as cancer or AIDS. The volunteers are tested for...