相关实验视频

Updated: Jan 8, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

通过透明的来源归因增强临床医生对大语言模型的信任:尿瘤学的随机对照评估

Nicolas Carl¹, Martin Joachim Hetz², Christoph Wies²

¹Department of Urology, University Medical Center Mannheim, Ruprecht-Karls University of Heidelberg, Mannheim, Germany; Division of Digital Prevention, Diagnostics and Therapy Guidance, German Cancer Research Center (DKFZ), Heidelberg, Germany.

European journal of cancer (Oxford, England : 1990)

|December 16, 2025

概括

使用检索增强生成 (RAG) 的新型泌尿器官聊天机器人UroBot在临床决策支持的准确性和源验证方面明显优于ChatGPT. 这种RAG方法提高了医疗应用中对AI的可靠性和信任.

科学领域:

人工智能在医学中的应用
泌尿瘤学临床决策支持

背景情况:

泌尿病学和瘤学的大型语言模型 (LLM) 面临着由于过时的数据和缺乏来源透明度的局限性.
这些局限性阻碍了临床可靠性和在医疗保健中采用人工智能工具.

研究的目的:

开发和评估UroBot,一个专门用于泌尿病的聊天机器人,增强了检索增强生成 (RAG).
为了比较UroBot与ChatGPT在提供准确和可验证的临床建议方面的表现.

主要方法:

UroBot是通过整合RAG来开发的,用于在线引用和源文本预览.
一项随机控制的读者研究比较了UroBot和ChatGPT在十个神经瘤病例中.
30名泌尿科医生评估了建议的正确性,来源可验证性和信任性.

主要成果:

与ChatGPT相比,UroBot表现出优越的推正确性 (73%对50%),来源归因 (74%对30%) 和可验证性 (84%对35%).
临床医生始终更喜欢UroBot的准确性,可验证性和信任性.
聊天GPT提供了模糊或不正确的引用,其中28%不存在/过时,83%缺乏特定部分,而UroBot实现了精确的引用对齐.

结论:

将LLM与RAG结合起来,比传统的LLM显著提高了来源归因和可验证性.
这种RAG增强的方法提供了可靠和最新的临床决策支持.
该方法在医学子专业之间是可转移的.

关键词:

聊天机器人聊天机器人可以解释的可解释性.在线参考在线参考检索增强生成的增强生成源文本预览源文本预览可验证性可验证性

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Patient-derived Orthotopic Xenograft Models for Human Urothelial Cell Carcinoma and Colorectal Cancer Tumor Growth and Spontaneous Metastasis

Patient-derived Orthotopic Xenograft Models for Human Urothelial Cell Carcinoma and Colorectal Cancer Tumor Growth and Spontaneous Metastasis

Published on: May 12, 2019

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

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...

Improving Translational Accuracy

Improving Translational Accuracy

Blinding

Blinding

Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.