在急诊室利用LLM进行早期诊断:比较临床BERT和GPT-4
Wanting Cui1, Joseph Finkelstein1
1Department of Biomedical Informatics, University of Utah, Salt Lake City, UT.
Studies in health technology and informatics
|August 8, 2025
概括
临床BERT和GPT-4模型被评估用于从早期临床笔记中识别诊断. 临床BERT表现出卓越的性能,特别是在呼吸系统疾病,显示出比GPT模型更高的精度和F1分数.
科学领域:
- 在医疗保健中的自然语言处理 (NLP)
- 临床信息学 临床信息学
- 人工智能 (AI) 在医学中的应用
背景情况:
- 电子健康记录 (EHR) 包含大量的非结构化的临床笔记.
- 利用自然语言处理 (NLP) 可以解锁临床决策支持的宝贵信息.
- 大型语言模型 (LLM) 在解释复杂的医疗文本方面表现有前途.
研究的目的:
- 使用早期临床笔记,比较ClinicalBERT和GPT-4的诊断识别能力.
- 为了评估特定疾病类别的模型性能:循环,呼吸,败血症和肺炎.
- 在临床环境中评估不同LLM的精度,回忆和F1分数.
主要方法:
- 使用了包含早期临床笔记的MIMIC-III数据集.
- 将ClinicalBERT与各种GPT模型 (包括GPT-4) 的性能进行比较.
- 基于其识别血液循环疾病,呼吸道疾病,败血症和肺炎的潜在诊断能力来评估模型.
主要成果:
- 在诊断识别准确度方面,ClinicalBERT的表现始终优于GPT模型.
- 临床BERT在呼吸系统疾病方面达到0.952的F1得分峰值.
- GPT模型的回忆力很高,但精度较低;GPT二进制投票方法的F1得分为0.784.4.
结论:
- 临床BERT表现出强大的精度和F1分数,使其成为从笔记中进行临床诊断的强大工具.
- GPT-4显示出具有高回忆力的潜力,但需要进一步改进,以便在此应用中提高精度.
- LLM为自动诊断支持提供了巨大的潜力,模型的选择取决于具体的性能需求 (精度与回忆).
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
579
08:04Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
Published on: June 6, 2025
500
相关概念视频
Pulmonary Tuberculosis IV
Tuberculosis, more commonly referred to as TB, is an infectious disease stemming from Mycobacterium tuberculosis. While it primarily impacts the lungs, TB can also affect other body areas. Given its severity and global impact, timely and accurate diagnosis is crucial for controlling its spread and improving patient outcomes.
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Serum Laboratory Studies, Stool Test, Breath Test
Gastrointestinal (GI) diagnostic studies are pivotal in confirming, ruling out, diagnosing, or staging various diseases, including cancers. Following diagnosis, allocating time for discussions with the patient and providing informational resources is crucial. Diagnostic assessments of the GI tract often occur in outpatient settings like endoscopy suites or GI labs. Preparation for these tests may include dietary restrictions, fasting, liquid bowel preparations, laxatives, enemas, and the...
Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test
In clinical practice, the direct measurement of hepatic blood flow to evaluate liver function presents significant challenges due to the intricate and specialized nature of the necessary techniques. Consequently, healthcare professionals often rely on empirical estimates derived from thorough patient examinations and liver function tests to gauge liver health. Among the tools at their disposal, the Child–Pugh and MELD scoring systems stand out for their ability to categorize and assess the...
