利用检索增强的大型语言模型与传统中医药的饮食建议 食品同质化:算法开发和验证
Hangyu Sha1,2, Fan Gong3, Bo Liu4
1School of Computer Science and Engineering, Southeast University, 2 Southeast University Road, Jiangning District, Nanjing, 210096, China, 86 15077889931.
JMIR medical informatics
|August 21, 2025
概括
本研究介绍了Yaoshi-RAG,该框架使用不确定的知识图 (UKG) 来改进基于药物食品同类学 (MFH) 的个性化传统中医 (TCM) 饮食建议的大型语言模型 (LLM). 该系统通过将结构化的TCM知识与LLM集成来提高准确性和可靠性.
科学领域:
- 综合医学
- 医疗保健中的人工智能
- 知识表示和推理
背景情况:
- 传统中国医学 (TCM) 使用药物食品同质 (MFH) 进行饮食疗法,但自动化受限于专家知识的依赖.
- 大型语言模型 (LLM) 在医疗保健领域具有前景, 但由于幻觉和知识缺口,
- 通过检索增强生成 (RAG) 将不确定的知识图 (UKG) 与LLM集成可以解决MFH应用的这些局限性.
研究的目的:
- 引入Yaoshi-RAG,这是一个旨在增强LLM的新框架,以生成基于MFH的准确和个性化的饮食建议.
- 利用UKG为LLM驱动的TCM饮食建议提供结构化,可靠和特定领域的知识.
主要方法:
- 使用LLM驱动的开放信息提取构建了一个全面的MFH知识图 (KG).
- 使用UKG的推理来衡量信任,并补充MFH KG中缺少的信息.
- 开发了一个检索流程,将用户查询与MFH KG连接起来,根据信心和对快速工程的重要性对推理路径进行排序.
主要成果:
- 在MFH KG中,有24,984个实体和29,292个三重企业;Yaoshi-RAG显著提高了LLM的业绩.
- 整合MFH KG导致LLM的Hits@1平均增加了14.5%,F1平均增加了8.7%.
- 使用Yaoshi-RAG的DeepSeek-R1获得了84.2%的Hits@1和71.5%的F1分数;人类评估证实了卓越的性能.
结论:
- 通过整合UKG获取的知识,Yaoshi-RAG有效地增强了基于MFH的饮食建议的LLM.
- 该框架成功地将传统的中医智慧与先进的人工智能结合起来,提供个性化,基于证据的饮食建议.
- 雅奥希-RAG展示了可靠和准确的TCM饮食建议的有希望的方法,
相关概念视频
01:14Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
727
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
727
01:26Pharmacokinetic Models: Comparison and Selection Criterion
490
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
490
01:28Methods of Medium Optimization
70
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...
70