大型语言模型在临床感染控制场景中的比较评估和性能:一项基准研究
Shuk-Ching Wong1,2,3, Edwin Kwan-Yeung Chiu3,4, Kelvin Hei-Yeung Chiu3,4
1Infection Control Team, Queen Mary Hospital, Hong Kong West Cluster, Hong Kong SAR, China.
Healthcare (Basel, Switzerland)
|October 29, 2025
概括
大型语言模型 (LLM) 在协助感染控制护士 (ICN) 决策方面表现有前途,但当前的AI工具对于自主使用是不可靠的. 关键错误强调了LLM需要支持,而不是取代ICN在感染预防和控制方面的专业知识.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 预防和控制感染的预防和控制.
背景情况:
- 感染预防和控制 (IPC) 在医院至关重要,依靠感染控制护士 (ICN).
- 评估大型语言模型 (LLM) 作为人工智能 (AI) 工具,以支持ICN在IPC决策中.
- 其目标是提高IPC的效率,安全性和准确性.
研究的目的:
- 在临床感染控制场景中对三个LLM (GPT-4.1,DeepSeek V3,Gemini 2.5 Pro Exp) 的性能进行比较.
- 评估人工智能产生的建议的连贯性,简洁性,有用性,相关性,证据质量和可操作性.
- 评估不同提示方法和专家背景对AI性能的影响.
主要方法:
- 一项涉及30个临床感染控制场景的横截面研究,在香港玛丽皇后医院.
- 使用开放式和结构化提示方法测试了三种LLM.
- 16名专家 (ICN和医生) 在1-10级别上对AI产生的建议进行了评分.
主要成果:
- GPT-4.1和DeepSeek V3的表现明显优于Gemini 2.5 Pro Exp (p < 0.001) 的表现.
- 结构化提示改善了证据质量 (p < 0.001);医生对结果的评价高于护士 (38.83对32.06,p < 0.001).
- 定性审查揭示了临床判断和所有模型的实际适用性中的关键错误,造成了安全风险.
结论:
- GPT-4.1和DeepSeek V3提供了有用的IPC建议,但尚未可靠自主使用.
- 由于临床判断的严重缺陷,LLM不能取代ICN的专业知识.
- 在IPC中,LLM应该作为辅助工具来支持,而不是自动化临床决策.
相关概念视频
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
Sputum Studies II: Culture and Sensitivity
1.1K
Description
Sputum culture and sensitivity is a medical procedure used to diagnose bacterial infections in the respiratory tract and select the most appropriate antibiotics for treatment. This process involves analyzing sputum samples of thick and opaque secretions produced in the lungs and airways. These samples are collected from patients and then sent to the laboratory for analysis.
The test can identify various pathogens responsible for respiratory infections, including Streptococcus,...
Sputum culture and sensitivity is a medical procedure used to diagnose bacterial infections in the respiratory tract and select the most appropriate antibiotics for treatment. This process involves analyzing sputum samples of thick and opaque secretions produced in the lungs and airways. These samples are collected from patients and then sent to the laboratory for analysis.
The test can identify various pathogens responsible for respiratory infections, including Streptococcus,...
1.1K
Sensitivity, Specificity, and Predicted Value
1.2K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
1.2K


