合成数据训练的开源语言模型是放射学报告专有模型的可行替代方案
Aakriti Pandita1, Angela Keniston1, Nikhil Madhuripan2
1Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
NPJ digital medicine
|July 23, 2025
概括
合成数据有效微调开源大语言模型 (LLMs) 用于放射文本转换. 这些模型的性能与专有GPT模型相美,提供了保护隐私的替代方案.
科学领域:
- 医疗信息学 医疗信息学
- 放射学中的人工智能
- 自然语言处理自然语言处理.
背景情况:
- 放射学中的自由文本指令对结构化数据提取提出了挑战.
- 像GPT这样的专有大型语言模型 (LLM) 很强大,但也引发了隐私问题.
- 开源的LLM为医疗数据处理提供了潜在的替代方案.
研究的目的:
- 评估使用合成数据微调开源LLM用于放射学文本到结构化数据转换的可行性.
- 将微调的开源LLM与GPT模型的性能进行比较.
- 评估开源LLM作为保护隐私的替代方案的可行性.
主要方法:
- 为培训生成了3000个合成甲状腺结节指令.
- 精心调整了六个开源的LLM (Starcoderbase,Mistral,Llama,Yi).
- 在50个MIMIC-III甲状腺结节指令上测试模型,与GPT-3.5和GPT-4 (0-shot,1-shot,5-shot) 进行比较.
主要成果:
- -34B和GPT-4 5-shot实现了最高的性能,没有显著的差异.
- 一些开源模型显著超过了GPT模型.
- 用合成数据训练的模型表现出与结构化文本转换的GPT模型相比的性能.
结论:
- 合成数据对于微调开源LLM用于放射学结构化数据提取是有效的.
- 开源的LLM显示性能与专有GPT模型相美.
- 开放的LLM为临床应用提供了一个保护隐私和可行的替代方案.
相关概念视频
Positron Emission Tomography
5.7K
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...
5.7K
Improving Translational Accuracy
11.9K
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...
11.9K
Radiological Investigation I: X-ray and CT
416
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
416
Magnetic Resonance Imaging
7.1K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
7.1K


