A collaborative large language model for drug analysis

doi:10.1038/s41551-025-01471-z

2025-09-23

DOI：10.1038/s41551-025-01471-z

原文链接

查看原文

摘要

En 中文

大型语言模型（LLMs），如ChatGPT，在理解人类咨询和生成具有人类级流利度的文本内容方面发挥了显著作用。然而，直接将LLMs应用于医疗保健领域面临若干问题。LLMs容易出现幻觉，即生成看似合理且真实的流畅内容，但实际上存在事实性错误。理想情况下，生成内容的来源应便于临床医生进行追溯和评估。我们提出了一种基于知识的协同大型语言模型DrugGPT，旨在提供准确、基于证据且可靠的推荐建议，以支持临床决策。DrugGPT整合了多种临床标准知识库，并引入了一种协同机制，该机制能够自适应地分析咨询内容，捕获相关知识来源，并在处理不同药物时对齐这些咨询内容与知识来源。我们在药物推荐、剂量推荐、不良反应识别、潜在药物相互作用识别以及回答一般药理学问题等方面对所提出的DrugGPT进行了评估。DrugGPT在参数量少于通用LLMs的情况下，超越了众多现有LLMs，并在所有指标上达到了当前最优性能。DrugGPT在回答与药物相互作用及推荐相关的问题方面超越了现有LLMs。

Keyword:

DrugGPT

large language models

drug recommendation

clinical decision support

knowledge grounding

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Nature Biomedical Engineering

IF:

26.6

论文数:

1.7K

被引数:

2.0W

机构

tencent jarvis lab

学者数:

论文数: 5

被引数: 0

GlaxoSmithKline

学者数:

1.8W

论文数: 9.6K

被引数: 39

University College London

学者数:

7.9W

论文数: 6.2W

被引数: 15.7W

university of oxford

学者数:

9.8W

论文数: 8.6W

被引数: 137

查看更多机构

引用论文

The DDI corpus: An annotated corpus with pharmacological substances and drug-drug interactions

JOURNAL OF BIOMEDICAL INFORMATICS

IF4.5

2013-10-01

289

OAAI

Herrero-Zazo, Maria; Segura-Bedmar, Isabel; Martinez, Paloma; Declerck, Thierry

Toward expert-level medical question answering with large language models 迈向专家级医疗问答的大语言模型

NATURE MEDICINE

IF50

2025-01-08

OAAI

Gottweis, Juraj; Sayres, Rory; Wulczyn, Ellery; Amin, Mohamed; Hou, Le; Clark, Kevin; Pfohl, Stephen R.; Neal, Darlene; Rashid, Qazi Mamunur; Schaekermann, Mike; Wang, Amy; Dash, Dev; Chen, Jonathan H.; Shah, Nigam H.; Lachgar, Sami; Mansfield, Philip Andrew; Prakash, Sushant; Green, Bradley; Dominowska, Ewa; Aguera y Arcas, Blaise; Tomasev, Nenad; Liu, Yun; Wong, Renee; Semturs, Christopher; Mahdavi, S. Sara; Barral, Joelle K.; Webster, Dale R.; Corrado, Greg S.; Matias, Yossi; Azizi, Shekoofeh; Karthikesalingam, Alan

Almanac — Retrieval-Augmented Language Models for Clinical Medicine 临床医学的历书检索增强语言模型

NEJM AI

IF0

2024-01-25

OAAI

Cyril Zakka; Rohan Shad; Akash Chaurasia; Alex R. Dalal; Jennifer L. Kim; Michael Moor; Robyn Fong; Curran Phillips; Kevin Alexander; Euan Ashley; Jack Boyd; Kathleen Boyd; Karen Hirsch; Curt Langlotz; Rita Lee; Joanna Melia; Joanna Nelson; Karim Sallam; Stacey Tullis; Melissa Ann Vogelsong; John Patrick Cunningham; William Hiesinger

ChatGPT and Other Large Language Models Are Double-edged Swords ChatGPT和其他大型语言模型是双刃剑

RADIOLOGY

IF15.2

2023-04-01

410

PREAI

Shen, Yiqiu; Heacock, Laura; Elias, Jonathan; Hentel, Keith D.; Reig, Beatriu; Shih, George; Moy, Linda

ChatGPT: the future of discharge summaries?

LANCET DIGITAL HEALTH

IF24.1

2023-03-01

350

PREAI

Patel, Sajan B.; Lam, Kyle

An extensive benchmark study on biomedical text generation and mining with ChatGPT

Bioinformatics

IF0

2023-09-08

OAAI

Qijie Chen; Haotong Sun; Haoyang Liu; Yinghui Jiang; Ting Ran; Xurui Jin; Xianglu Xiao; Zhimin Lin; Hongming Chen; Zhangmin Niu

Large language models encode clinical knowledge 大型语言模型对临床知识进行编码

Nature

IF0

2023-07-12

OAAI

Karan Singhal; Shekoofeh Azizi; Tao Tu; S. Sara Mahdavi; Jason Wei; Hyung Won Chung; Nathan Scales; Ajay Tanwani; Heather Cole-Lewis; Stephen Pfohl; Perry Payne; Martin Seneviratne; Paul Gamble; Chris Kelly; Abubakr Babiker; Nathanael Schärli; Aakanksha Chowdhery; Philip Mansfield; Dina Demner-Fushman; Blaise Agüera y Arcas; Dale Webster; Greg S. Corrado; Yossi Matias; Katherine Chou; Juraj Gottweis; Nenad Tomasev; Yun Liu; Alvin Rajkomar; Joelle Barral; Christopher Semturs; Alan Karthikesalingam; Vivek Natarajan

ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports

European Radiology

IF0

2023-10-05

OAAI

Katharina Jeblick; Balthasar Schachtner; Jakob Dexl; Andreas Mittermeier; Anna Theresa Stüber; Johanna Topalis; Tobias Weber; Philipp Wesp; Bastian Oliver Sabel; Jens Ricke; Michael Ingrisch

MIMIC-IV, a freely accessible electronic health record dataset Mimic-iv，一个可自由访问的电子健康记录数据集

Scientific Data

IF0

2023-01-03

OAAI

Alistair E. W. Johnson; Lucas Bulgarelli; Lu Shen; Alvin Gayles; Ayad Shammout; Steven Horng; Tom J. Pollard; Sicheng Hao; Benjamin Moody; Brian Gow; Li-wei H. Lehman; Leo A. Celi; Roger G. Mark

Quinine, an old anti-malarial drug in a modern world: role in the treatment of malaria 奎宁，现代世界中一种古老的抗疟疾药物: 在疟疾治疗中的作用

Malaria Journal

IF0

2011-05-24

OAAI

Jane Achan; Ambrose O Talisuna; Annette Erhart; Adoke Yeka; James K Tibenderana; Frederick N Baliraine; Philip J Rosenthal; Umberto D'Alessandro

查看更多内容