开源大型语言模型的性能,从临床笔记中提取症状
Yunbing Bai1, Wanting Cui1, Joseph Finkelstein1
1Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah.
Studies in health technology and informatics
|August 8, 2025
概括
大型语言模型 (LLM) 在从临床笔记中提取症状,征兆和ICD-10代码方面表现有前途. 拉玛3.3-70B在这个自动化临床数据提取任务中表现出卓越的表现.
科学领域:
- 在医疗保健中的自然语言处理 (NLP)
- 临床信息学 临床信息学
- 人工智能 (AI) 在医学中的应用
背景情况:
- 从电子健康记录 (EHR) 中自动提取临床信息对于提高医疗保健效率至关重要.
- 大型语言模型 (LLM) 提供了分析非结构化临床文本的潜力.
- 评估LLM在特定临床任务上的表现,如症状提取和编码是必不可少的.
研究的目的:
- 评估开源基础大语言模型 (LLM) 在从临床笔记中提取症状和征兆 (S&S) 和相应的ICD-10代码方面的能力.
- 为了比较不同版本的Llama模型 (Llama 3.1-13B,Llama 3.3-70B,Me-Llama-13B) 在S&S提取和ICD-10代码生成方面的性能.
主要方法:
- 利用公开的MTSamples数据集,专注于生殖尿路疾病.
- 手动注释数据集的一个子集,用于基准真相比较.
- 评估了三种Llama模型版本的S&S提取和ICD-10代码生成任务,测量一致性,运行时间和性能指标 (回忆,精度).
主要成果:
- 拉玛3.3-70B在测试模型中显示出最好的整体性能.
- 这个模型实现了快速运行时间和高一致性.
- 对于S&S提取,Llama 3.3-70B报告了平均回忆率为0.87和精度为0.71.
- 对于ICD-10代码生成,它实现了0.71的平均回忆率和0.54的精度.
结论:
- 开源的LLM,特别是Llama 3.3-70B,是从临床笔记中自动提取症状,征兆和ICD-10代码的有效工具.
- 这些发现表明,LLM有很大的潜力来简化医疗保健环境中的临床数据处理和编码.
- 进一步的研究可以探索针对各种临床数据集和复杂的编码要求优化LLM性能.
更多相关视频
07:50A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
16.0K
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
579
相关概念视频
Classification of Illness
7.9K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
7.9K
Statistical Software for Data Analysis and Clinical Trials
789
Statistical software is pivotal in data analysis and clinical trials by providing tools to analyze data, draw conclusions, and make predictions. These software packages range from simple data management applications to complex analytical platforms, supporting various statistical tests, models, and simulation techniques. Their significance lies in their ability to handle vast amounts of data with precision and efficiency, enabling researchers to validate hypotheses, identify trends, and make...
789
Improving Translational Accuracy
2.7K
2.7K
