大型语言模型在病学中的临床应用和局限性:系统性审查
Zoe Unger1, Shelly Soffer2,3, Orly Efros3,4
1First Faculty of Medicine, Charles University, Prague, Czech Republic.
大型语言模型 (LLM) 在科中显示出对患者教育和工作流的优化有希望. 然而,由于输入依赖性和有限的验证,它们的临床整合需要进一步研究.
科学领域:
- 腎臟病學 (nephrology) 是一種醫學.
- 人工智能的人工智能
- 医疗信息学 医疗信息学
背景情况:
- 大型语言模型 (LLM) 正在成为医疗保健中的潜在工具.
- 本系统性审查的重点是脏病学中的文本生成对话LLM.
研究的目的:
- 评估LLM在科的应用.
- 在临床科实践中确定LLMs的优点和局限性.
主要方法:
- 在PubMed,科学网,Embase和Cochrane图书馆进行系统搜索.
- 遵守系统审查和元分析 (PRISMA) 准则的首选报告项目.
- 在PROSPERO的注册号是CRD42024550169.9.
主要成果:
- 23项研究评估了LLM在患者教育,工作流程优化,脏饮食指导和实验室数据解释方面的应用.
- 经过LLM的研究,可读性,慢性病信息的准确性,报警管理和饮食含量分类得到了改善.
- 像GPT-4,Gemini,Bard AI,Bing Chat和Copilot这样的特定模型在不同科任务中显示出不同的强度.
结论:
- 虽然LLM显示出增强脏病学实践的潜力,但其广泛采用是过早的.
- 输入质量和有限的外部验证是关键的限制.
- 进一步的研究对于安全的临床整合和现实世界的可行性至关重要.
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
09:16Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
相关概念视频
Renal Drug Clearance: Overview
Renal clearance can be calculated using different methods. One approach is to divide the urinary drug excretion rate by the plasma drug concentration. This method directly measures renal clearance, indicating the kidneys' efficiency in...
Chronic Kidney Disease III: Interprofessional Care
Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
Drug Dosing in Renal Diseases: Dose Adjustments Based on Drug Clearance and Elimination Rate Constant
Renal Drug Clearance: Comparison Between Renal Excretion Methods
Renal clearance is often associated with the renal glomerular filtration rate (GFR), which represents the rate at which plasma is filtered through the glomeruli in the kidney. When drug reabsorption is minimal and there is no active secretion, renal clearance is closely related to the...
Chronic Kidney Disease II: Clinical Manifestations
