使用合成医疗保健数据来利用大型语言模型进行命名实体识别:开发和验证研究
Hendrik Šuvalov1, Mihkel Lepson1, Veronika Kukk1
1Institute of Computer Science, University of Tartu, Tartu, Estonia.
Journal of medical Internet research
|March 18, 2025
概括
本研究引入了一种创新的方法,用于创建爱沙尼亚医疗命名实体识别 (NER) 模型,使用由大语言模型 (LLM) 生成的合成数据. 这种方法克服了低资源语言的数据稀缺性,同时保持了患者的隐私.
科学领域:
- 自然语言处理自然语言处理.
- 医疗信息学 医疗信息学
- 计算语言学 计算语言学
背景情况:
- 命名实体识别 (NER) 对于从健康记录中提取医疗信息至关重要.
- 为爱沙尼亚语等资源较少的语言开发NER是具有挑战性的,因为注释数据有限.
- 大型语言模型 (LLM) 对跨语言和域的文本理解有希望.
研究的目的:
- 为爱沙尼亚语开发医疗NER模型,爱沙尼亚语是一种资源较低的语言.
- 使用LLMs为NER模型培训生成合成爱沙尼亚健康数据.
- 通过避免真实世界的注释数据来保护患者数据隐私.
主要方法:
- 一个三步管道:合成数据生成 (GPT-2),LLM注释 (GPT-3.5-Turbo,GPT-4) 和NER模型微调.
- 不同的LLM提示和模型 (GPT-3.5-Turbo,GPT-4,本地LLM) 的比较.
- 探讨合成数据量对NER模型性能的影响.
主要成果:
- 该方法显示了从现实世界的文本中提取医疗实体的潜力.
- 最好的设置在药物提取方面获得了0.69的F1得分,在程序提取方面达到0.38.
- 性能因实体类型而异,取出程序更为复杂.
结论:
- 通过合成数据有效地利用LLM来训练NER模型,保护患者的隐私.
- 这种方法为开发爱沙尼亚语等低资源语言的NER模型提供了有希望的解决方案.
- 未来的工作将集中在完善合成数据生成和扩大适用于其他领域和语言.
关键词:
爱沙尼亚语 爱沙尼亚语在法学士 (LLM) 课程中.尼尔·内尔 (NER NER NER) 是一个国家.在NLP中,我们使用了NLP.有注释的数据.人工智能的人工智能是人工智能.临床决策支持 临床决策支持数据注释数据注释数据挖掘是数据挖掘的一个方法.医疗保健数据 医疗保健数据语言模型语言模型大型语言模型机器学习是机器学习.医疗实体是一个医疗实体.命名实体的认可 命名实体的认可自然语言处理自然语言处理.综合数据 综合数据更多相关视频
07:50A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
15.7K
09:20Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
Published on: February 23, 2019
8.6K
相关概念视频
Synthetic Biology
4.7K
Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...
Golden rice
Golden rice is a genetically modified...
4.7K
lncRNA - Long Non-coding RNAs
2.8K
2.8K
RNA-seq
9.7K
RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases.
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
9.7K
Improving Translational Accuracy
8.5K
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...
8.5K
Drug Nomenclature
1.5K
During the development of a new pharmaceutical, the manufacturer initially assigns a code name to the drug. Once approved, the drug receives a United States Adopted Name (USAN)—a generic, nonproprietary designation. Upon being listed in the United States Pharmacopeia, this nonproprietary name becomes the drug's official name. Additionally, the manufacturer assigns a proprietary name or trademark, which serves as the brand name under which the drug is marketed. It is worth noting that...
1.5K
Genetic Lingo
98.9K
Overview
98.9K
