相关实验视频

Updated: Jan 15, 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

大型语言模型在复杂临床病例中的应用:横截面评估研究

Yuanheng Huang¹, Guozhen Yang¹, Yahui Shen²

¹Department of Cardiothoracic Surgery, Third Affiliated Hospital of Sun Yat-sen University, 2693 Kaichuang Avenue, Huangpu District, Guangzhou, 510000, China, 86 13922192727, 86 82179042.

JMIR medical informatics

|October 7, 2025

概括

大型语言模型 (LLM) 显示了医疗决策支持的巨大潜力,比人类专家提供更快,更具成本效益的解决方案. 对于临床应用,GPTo1和Deepseek-R1特别有前途.

科学领域:

医疗信息学医疗信息学
医疗保健中的人工智能
临床决策支持系统临床决策支持系统

背景情况:

大型语言模型 (LLM) 对医疗应用有希望,但面临挑战.
自然语言处理 (NLP) 的进步推动了LLM的发展.
将LLMs纳入临床实践需要仔细评估.

研究的目的:

在复杂的医疗病例中评估LLM的效率,准确性和成本效益.
评估LLM作为临床决策支持工具的潜力.
将LLM绩效与传统的专家决策进行比较.

主要方法:

用心胸外科手术80个复杂病例对多个LLM进行评估.
评估LLM决策时间,准确性 (利克尔特分数) 和成本.
对LLM绩效指标与专家决策时间进行比较.

主要成果:

在决策速度方面,LLM显著超过专家 (不到4分钟,而不是33.6分钟).
与其他模型相比,Deepseek-R1和GPTo1显示出更高的准确性和更低的幻觉率.
所有评估的LLM都比多学科团队的决策成本要低得多,像Deepseek-R1这样的开源模型提供零直接成本.

结论:

由于提高效率,准确性和降低成本,GPTo1和Deepseek-R1具有强大的临床潜力.
GPT4o和Kimi表现中等,适合更广泛的临床任务.
在临床决策中需要进一步验证LLaMa3系列和Gemini模型.

关键词:

人工智能的人工智能是人工智能.临床决策支持临床决策支持复杂的医疗病例复杂的医疗病例跨部门的研究.大型语言模型.

更多相关视频

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

相关概念视频

Longitudinal Studies

Longitudinal Studies

Longitudinal studies are also widely used in other medical and social science fields. For instance, in cardiovascular research, they can monitor patients' health over decades to identify risk factors for heart disease, such as high cholesterol or smoking, and evaluate the long-term effectiveness of preventive measures. Similarly, in mental health studies, researchers might follow individuals from adolescence into adulthood to understand the development and progression of conditions like...