相关实验视频

Updated: May 23, 2025

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

使用大型语言模型作为临床决策支持工具来管理胰腺腺癌,使用国家综合癌症网络指南

Kristen N Kaiser¹, Alexa J Hughes², Anthony D Yang³

¹Surgical Outcomes and Quality Improvement Center (SOQIC), Department of Surgery, Indiana School of Medicine, Indianapolis, IN. Electronic address: https://twitter.com/kristen_kaiser1.

|March 7, 2025

概括

大型语言模型 (LLM) 对胰腺癌护理指南的准确性有限. 这些人工智能工具在临床使用之前需要大幅改进,因为它们经常存在不准确性和多言多语.

科学领域:

在瘤学中使用人工智能
临床决策支持系统临床决策支持系统
医疗信息学医疗信息学

背景情况:

大型语言模型 (LLM) 显示了胰腺管道腺癌 (PDAC) 中临床决策支持的潜力.
目前的LLM可能会提高符合指南的护理率.
评估LLM准确性和一致性对于医疗保健整合至关重要.

研究的目的:

评估两个公共LLM (ChatGPT,Copilot) 的第一通准确度,与NCCN对PDAC的指导方针相比.
评估每个法学士课程中的响应一致性.
比较两个LLM之间的准确性和多言多语.

主要方法:

根据NCCN PDAC指南开发了基于临床场景.
在ChatGPT和微软Copilot中输入提示,每个场景生成四个响应.
手动对答案的准确性和语言性进行了分级,并将其与临床医生生成的答案进行了比较.

主要成果:

在104个答案中,LLMs实现了42%的完全准确性.
聊天GPT (52%准确率) 的表现优于Copilot (33%准确率).
法学士的回复比临床医生的回复 (32个字) 更多言多语 (270个字).

结论:

公开提供的LLM在解决PDAC临床问题时表现出显著的不准确性和多言多语.
目前的LLM需要在部署为医疗保健中的临床决策支持工具之前进行大量优化.
需要进一步开发以确保临床应用的可靠性和简洁性.

更多相关视频

An Orthotopic Resectional Mouse Model of Pancreatic Cancer

An Orthotopic Resectional Mouse Model of Pancreatic Cancer

Published on: September 24, 2020

Utilizing High Resolution Ultrasound to Monitor Tumor Onset and Growth in Genetically Engineered Pancreatic Cancer Models

Utilizing High Resolution Ultrasound to Monitor Tumor Onset and Growth in Genetically Engineered Pancreatic Cancer Models

Published on: April 7, 2018

相关概念视频

Chronic Pancreatitis II: Collaborative Care

Chronic Pancreatitis II: Collaborative Care

The management of chronic pancreatitis is multifaceted, involving a comprehensive approach that includes thorough assessment, diagnostic testing, and a variety of management strategies.
Assessment:

Cancer Survival Analysis

Cancer Survival Analysis

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...