相关实验视频

Updated: Jun 11, 2025

In Vivo Modeling of the Morbid Human Genome using Danio rerio

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

一个混合框架与大型语言模型用于罕见疾病表型

Jinge Wu^1,2, Hang Dong³, Zexi Li⁴

¹Institute of Health Informatics, University College London, London, UK. jinge.wu.20@ucl.ac.uk.

BMC medical informatics and decision making

|October 7, 2024

概括

使用自然语言处理 (NLP) 和大语言模型 (LLM) 的新混合方法显著改善了从临床笔记中识别罕见疾病. 这种方法通过发现以前未被识别的患者病例来提高早期诊断.

科学领域:

医疗信息学医疗信息学
计算语言学计算语言学
罕见疾病研究罕见疾病研究

背景情况:

由于患病率低,症状多样化,罕见疾病存在诊断和治疗方面的挑战.
非结构化临床笔记丰富的诊断信息,但很难手动分析.
需要自动化方法来有效和准确地从临床文本中识别罕见疾病.

研究的目的:

开发和评估一种混合框架,以从非结构化的临床报告中加强罕见疾病的识别.
将基于字典的NLP工具与大型语言模型 (LLM) 结合起来,以提高准确性.
利用现有的本体学来创建全面的罕见病词汇.

主要方法:

综合孤儿网罕见疾病本体学 (ORDO) 和统一医疗语言系统 (UMLS) 为罕见疾病词汇.
使用SemEHR,一个基于字典的NLP工具,用于最初的罕见疾病提取提取.
雇佣了各种LLM (LLaMA3,Phi3-mini,OpenBioLLM,BioMistral) 与不同的提示策略 (零射击,少数射击,知识增强生成).

主要成果:

混合方法在罕见疾病识别方面表现优于传统的NLP和独立的LLM.
LLaMA3和Phi3-mini获得了最高的F1分数,其中少数射击提示 (1-3个例子) 是最有效的.
该方法确定了许多潜在的罕见疾病病例,这些病例被结构化诊断记录遗漏了.

结论:

混合NLP-LLM方法在改善从临床笔记中识别罕见疾病方面显示出显著的希望.
这种方法可以发现以前未被识别的罕见疾病病例,帮助早期诊断.
进一步的研究应侧重于本体学映射,重叠病例识别和临床整合.

关键词:

电子健康记录电子健康记录大型语言模型.自然语言处理自然语言处理.现型化 (Phenotyping) 是一种表现方式.

更多相关视频

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

相关概念视频

Genome-wide Association Studies-GWAS

Genome-wide Association Studies-GWAS

Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...

Incomplete Dominance

Incomplete Dominance

Gregor Mendel's work (1822 - 1884) was primarily focused on pea plants. Through his initial experiments, he determined that every gene in a diploid cell has two variants called alleles inherited from each parent. He suggested that amongst these two alleles, one allele is dominant in character and the other recessive. The combination of alleles determines the phenotype of a gene in an organism.