A SNAPpy使用大语言模型:使用大语言模型来对儿科急性中耳炎的治疗计划进行分类
Jessica J Pourian1, Ben Michaels2, Anh Vo3
1Division of Clinical Informatics and Digital Transformation, Department of Pediatrics, University of California, San Francisco, San Francisco, CA 94143, United States.
Journal of the American Medical Informatics Association : JAMIA
|October 10, 2025
概括
一个新的AI工具Versa准确地识别医生笔记中的急性中耳炎 (AOM) 治疗计划,帮助抗生素管理工作. 这项技术有助于跟踪处方模式,减少儿童过度使用抗生素.
科学领域:
- 人工智能在医学中的应用
- 儿童传染病 儿童传染病
- 医疗信息学 医疗信息学
背景情况:
- 急性中耳炎 (AOM) 显著导致儿童过度使用抗生素.
- 安全网抗生素处方 (SNAP) 对抗生素管理至关重要,但难以确定.
- 缺乏结构化的文档阻碍了SNAP的识别.
研究的目的:
- 为了验证Versa的准确性,基于GPT-4o的大型语言模型 (LLM),在分类AOM治疗计划.
- 评估Versa作为改善儿科抗生素管理质量的工具的实用性.
- 为了比较Versa的性能与微调的模型和手动审查.
主要方法:
- 对儿科AOM遭遇的回顾性横截面研究.
- 使用Versa的多个提示策略来分类治疗计划.
- 经过验证的LLM分类与两名儿科医生的手册审查对比.
- 将Versa的准确性与当地微调的临床长型模型进行了比较.
主要成果:
- 在分类AOM治疗计划时,Versa实现了97.8%的零射击精度和85%的少数射击精度.
- 临床-长型仪表显示了93.3%的准确性.
- 这项研究分析了5707次接触,其中374次是手动审查的.
结论:
- 维萨从医生笔记中准确地识别了AOM治疗计划.
- 维尔萨提供了一个具有成本效益的工具,用于跟踪儿科抗生素管理中的处方做法.
- 该LLM促进质量改进举措,以打击过度使用抗生素.
更多相关视频
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
1.0K
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
432
相关概念视频
01:26Tonsillitis II: Management
This lesson will focus on the different treatment options for managing tonsillitis, which typically depend on the cause and severity.
01:17Introduction to Language of Pathophysiology ll
This lesson explores key terms that describe how diseases progress, their outcomes, and their distribution in populations.Diagnostic tests identify diseases and monitor treatment. These include blood and urine tests, biopsies, imaging (X-ray, MRI), and detection of infectious agents.Remission is a reduction or disappearance of symptoms.Exacerbation refers to the worsening of symptoms, such as increased wheezing during an asthma attack.A precipitating factor triggers an acute episode, while a...