相关实验视频

Updated: Sep 10, 2025

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

使用大型语言模型进行上下文学习:一种简单有效的方法来改善放射学报告的标记

Songsoo Kim¹, Donghyun Kim², Jaewoong Kim¹

¹Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Korea.

Healthcare informatics research

|August 21, 2025

概括

使用生成预训练变压器-4 (GPT-4) 的上下文学习显著改善了放射学报告的标签. 这种方法提高了主观和客观任务的准确性,为研究人员提供了实际解决方案.

科学领域:

医疗成像中的人工智能
在医疗保健中的自然语言处理
放射学报告分析

背景情况:

放射学报告的自动标记对于有效的数据分析和临床见解至关重要.
预训练型转换器-4 (GPT-4) 显示了复杂的自然语言理解任务的潜力.

研究的目的:

用GPT-4评估背景学习的有效性,用于标记放射学报告.
将标准提示与上下文提示进行比较,以提高标签准确性.

主要方法:

使用MIMIC-III数据库中的放射学报告进行了回顾性研究.
在头部和腹部CT报告中进行多标签分类的基本和上下文提示的比较.
优化实验以评估一致性和错误率.

主要成果:

使用GPT-4的上下文学习显著提高了头部CT报告的F1分数,特别是"异物体"和"质量"标签.
在使用上下文提示的腹部CT报告中,在所有标签上观察到显著的性能增长.
阅读器间的准确性很高,表明了可靠的基线性能.

结论:

使用GPT-4的上下文学习始终提高了放射学报告的标签准确性.
这种方法有效地使模型标准与主观和客观标签任务的人类注释符保持一致.
该方法实用,可适应,适用于放射学研究中的各种标签应用.

关键词:

人工智能计算机辅助诊断医疗信息学自然语言处理放射学

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

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...