利用检索增强生成技术捕捉精准肿瘤学中的分子驱动治疗关系。

Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology.

机构信息

Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins School of Medicine, Baltimore, MD, USA.

The Johns Hopkins Molecular Tumor Board, Johns Hopkins School of Medicine, Baltimore, MD, USA.

出版信息

Stud Health Technol Inform. 2024 Aug 22;316:983-987. doi: 10.3233/SHTI240575.

DOI:10.3233/SHTI240575

PMID:39176956

Abstract

Modern generative artificial intelligence techniques like retrieval-augmented generation (RAG) may be applied in support of precision oncology treatment discussions. Experts routinely review published literature for evidence and recommendations of treatments in a labor-intensive process. A RAG pipeline may help reduce this effort by providing chunks of text from these publications to an off-the-shelf large language model (LLM), allowing it to answer related questions without any fine-tuning. This potential application is demonstrated by retrieving treatment relationships from a trusted data source (OncoKB) and reproducing over 80% of them by asking simple questions to an untrained Llama 2 model with access to relevant abstracts.

摘要

现代生成式人工智能技术，如检索增强生成（RAG），可应用于支持精准肿瘤治疗讨论。专家通常会查阅已发表的文献，以获取治疗方法的证据和建议，这是一个劳动密集型过程。RAG 管道可以通过从这些出版物中检索文本块并将其提供给现成的大型语言模型（LLM），从而帮助减少这方面的工作量，使 LLM 能够回答相关问题而无需进行任何微调。通过从可信数据源（OncoKB）中检索治疗关系，并向未经训练的、可访问相关摘要的 Llama 2 模型简单提问，该潜在应用可重现 80%以上的关系，从而证明了这一点。