Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Guangyi, Zhang, Yongqi, Liu, Xunyuan, Yao, Quanming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912401073373184
author Liu, Guangyi
Zhang, Yongqi
Liu, Xunyuan
Yao, Quanming
author_facet Liu, Guangyi
Zhang, Yongqi
Liu, Xunyuan
Yao, Quanming
contents Drug-drug interaction (DDI) prediction is critical for treatment safety. While large language models (LLMs) show promise in pharmaceutical tasks, their effectiveness in DDI prediction remains challenging. Inspired by the well-established clinical practice where physicians routinely reference similar historical cases to guide their decisions through case-based reasoning (CBR), we propose CBR-DDI, a novel framework that distills pharmacological principles from historical cases to improve LLM reasoning for DDI tasks. CBR-DDI constructs a knowledge repository by leveraging LLMs to extract pharmacological insights and graph neural networks (GNNs) to model drug associations. A hybrid retrieval mechanism and dual-layer knowledge-enhanced prompting allow LLMs to effectively retrieve and reuse relevant cases. We further introduce a representative sampling strategy for dynamic case refinement. Extensive experiments demonstrate that CBR-DDI achieves state-of-the-art performance, with a significant 28.7% accuracy improvement over both popular LLMs and CBR baseline, while maintaining high interpretability and flexibility.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23034
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction
Liu, Guangyi
Zhang, Yongqi
Liu, Xunyuan
Yao, Quanming
Artificial Intelligence
Machine Learning
Drug-drug interaction (DDI) prediction is critical for treatment safety. While large language models (LLMs) show promise in pharmaceutical tasks, their effectiveness in DDI prediction remains challenging. Inspired by the well-established clinical practice where physicians routinely reference similar historical cases to guide their decisions through case-based reasoning (CBR), we propose CBR-DDI, a novel framework that distills pharmacological principles from historical cases to improve LLM reasoning for DDI tasks. CBR-DDI constructs a knowledge repository by leveraging LLMs to extract pharmacological insights and graph neural networks (GNNs) to model drug associations. A hybrid retrieval mechanism and dual-layer knowledge-enhanced prompting allow LLMs to effectively retrieve and reuse relevant cases. We further introduce a representative sampling strategy for dynamic case refinement. Extensive experiments demonstrate that CBR-DDI achieves state-of-the-art performance, with a significant 28.7% accuracy improvement over both popular LLMs and CBR baseline, while maintaining high interpretability and flexibility.
title Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.23034