A collaborative large language model for drug analysis

Large language models (LLMs), such as ChatGPT, have substantially helped in understanding human inquiries and generating textual content with human-level fluency. However, directly using LLMs in healthcare applications faces several problems. LLMs are prone to produce hallucinations, or fluent content that appears reasonable and genuine but that is factually incorrect. Ideally, the source of the generated content should be easily traced for clinicians to evaluate. We propose a knowledge-grounded collaborative large language model, DrugGPT, to make accurate, evidence-based and faithful recommendations that can be used for clinical decisions. DrugGPT incorporates diverse clinical-standard knowledge bases and introduces a collaborative mechanism that adaptively analyses inquiries, captures relevant knowledge sources and aligns these inquiries and knowledge sources when dealing with different drugs. We evaluate the proposed DrugGPT on drug recommendation, dosage recommendation, identification of adverse reactions, identification of potential drug-drug interactions and answering general pharmacology questions. DrugGPT outperforms a wide range of existing LLMs and achieves state-of-the-art performance across all metrics with fewer parameters than generic LLMs.

Authors

Institutions

Publication Details

Journal
Nature Biomedical Engineering
Published
2025-09-23
DOI
https://doi.org/10.1038/s41551-025-01471-z
Citations
6
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
14.89

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A collaborative large language model for drug analysis

Patrick Schwab, Anshul Thakur, Hongjian Zhou, Yefeng Zheng et al.
6 citations
Nature Biomedical Engineering
Machine Learning in Healthcare
14.89
article

A collaborative large language model for drug analysis

Patrick Schwab, Anshul Thakur, Hongjian Zhou, Yefeng Zheng, Lei Clifton, David W. Eyre, Guowei Huang, Xian Wu, Wenjun Zhang, Fenglin Liu, David A. Clifton, Kim Branson, Jinge Wu, F. Liu, Haochen Luo
article en
6 citations

Abstract

Large language models (LLMs), such as ChatGPT, have substantially helped in understanding human inquiries and generating textual content with human-level fluency. However, directly using LLMs in healthcare applications faces several problems. LLMs are prone to produce hallucinations, or fluent content that appears reasonable and genuine but that is factually incorrect. Ideally, the source of the generated content should be easily traced for clinicians to evaluate. We propose a knowledge-grounded collaborative large language model, DrugGPT, to make accurate, evidence-based and faithful recommendations that can be used for clinical decisions. DrugGPT incorporates diverse clinical-standard knowledge bases and introduces a collaborative mechanism that adaptively analyses inquiries, captures relevant knowledge sources and aligns these inquiries and knowledge sources when dealing with different drugs. We evaluate the proposed DrugGPT on drug recommendation, dosage recommendation, identification of adverse reactions, identification of potential drug-drug interactions and answering general pharmacology questions. DrugGPT outperforms a wide range of existing LLMs and achieves state-of-the-art performance across all metrics with fewer parameters than generic LLMs.

Nature Biomedical Engineering
GlaxoSmithKline (United Kingdom) (GB), Tencent (China) (CN), Open Data Institute (GB), Westlake University (CN), University of Oxford (GB), Nuffield Health (GB), Suzhou Research Institute (CN), Science Oxford (GB), University College London (GB)
Wellcome Trust, UK Research and Innovation, National Institute for Health and Care Research, Department of Health and Social Care, Royal Academy of Engineering, University of Oxford, Oxford Health NHS Foundation Trust, Engineering and Physical Sciences Research Council, Clarendon Fund
Openalex Percentile: Top 1%
Machine Learning in Healthcare
14.89
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.