通过"短拍"提示来提高ChatGPT和DeepSeek的CAD-RADSTM 2.0类别分配性能
1Department of Radiology, School of Medicine, Bursa Uludağ University, Bursa, Turkey.
Journal of computer assisted tomography
|September 26, 2025
概括
低射击提示显著改善了大型语言模型在赋予冠状动脉疾病报告和数据系统 (CAD-RADSTM 2.0) 类别方面的性能,实现了高精度和消除幻觉.
科学领域:
- 医疗成像中的人工智能
- 用于放射学报告的自然语言处理
- 机器学习用于临床决策支持
背景情况:
- 大型语言模型 (LLM) 在医学文本分析中表现有前途.
- 对冠状动脉疾病报告和数据系统 (CAD-RADSTM 2.0) 的准确分类对于患者管理至关重要.
- 在CAD-RADSTM 2.0分类中,LLM使用几次射击提示的性能尚未得到充分证实.
研究的目的:
- 为了评估少数射击提示对ChatGPT和DeepSeek LLMs在CAD-RADSTM 2.0类别分配中的性能的影响.
- 为了比较基于LLM的CAD-RADSTM 2.0分类与放射科医生评估的准确性和可重复性.
主要方法:
- 通过使用基于CAD-RADSTM 2.0框架的MIMIC-IV数据库中的20个报告开发了几次的提示.
- 100份MIMIC-IV报告使用使用ChatGPT和DeepSeek的零射击和少数射击提示进行分类.
- 模型的性能与参考放射科医生的分类进行了评估,并使用麦克纳马测试和科恩卡帕进行了统计分析.
主要成果:
- 零射击提示产生了较低的准确性 (ChatGPT: 14%,DeepSeek: 8%) 与频繁的幻觉.
- 短射击提示显著提高了准确度,为ChatGPT的98%和DeepSeek的93% (P<0.001),消除了幻觉.
- 在LLM生成和放射学家分类之间观察到很高的一致性 (kappa > 0.91),具有很好的可重现性.
结论:
- 短拍提示大大提高了用于CAD-RADSTM 2.0分类的LLM准确性.
- 这种方法表明了在心血管成像解释中临床整合的潜力.
- 通过几次拍摄提示优化的LLM可以促进CAD-RADSTM 2.0.0的高效和准确的采用.
更多相关视频
05:58Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
Published on: August 29, 2018
9.3K
08:17A Semantic Priming Event-related Potential ERP Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder
Published on: April 12, 2018
11.1K
相关概念视频
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
1.6K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.6K
Force Classification
2.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.3K
Positron Emission Tomography
6.9K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
6.9K
Improving Translational Accuracy
3.5K
3.5K
Improving Translational Accuracy
14.1K
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...
14.1K
