GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation

TL;DR

This paper introduces GAP, a graph-assisted prompt framework that enhances dialogue-based medication recommendations by extracting medical concepts and integrating external knowledge to improve accuracy and safety.

Contribution

GAP is a novel framework that constructs patient-centric graphs from dialogues and leverages external medical knowledge to improve LLM-based medication recommendations.

Findings

GAP outperforms strong baselines in dialogue-based medication recommendation tasks.

It effectively incorporates medical concepts and external knowledge to reduce non-factual responses.

GAP shows promising results in dynamic diagnostic interviewing scenarios.

Abstract

Medication recommendations have become an important task in the healthcare domain, especially in measuring the accuracy and safety of medical dialogue systems (MDS). Different from the recommendation task based on electronic health records (EHRs), dialogue-based medication recommendations require research on the interaction details between patients and doctors, which is crucial but may not exist in EHRs. Recent advancements in large language models (LLM) have extended the medical dialogue domain. These LLMs can interpret patients' intent and provide medical suggestions including medication recommendations, but some challenges are still worth attention. During a multi-turn dialogue, LLMs may ignore the fine-grained medical information or connections across the dialogue turns, which is vital for providing accurate suggestions. Besides, LLMs may generate non-factual responses when there is a lack of domain-specific knowledge, which is more risky in the medical domain. To address these challenges, we propose a \textbf{G}raph-\textbf{A}ssisted \textbf{P}rompts (\textbf{GAP}) framework for dialogue-based medication recommendation. It extracts medical concepts and corresponding states from dialogue to construct an explicitly patient-centric graph, which can describe the neglected but important information. Further, combined with external medical knowledge graphs, GAP can generate abundant queries and prompts, thus retrieving information from multiple sources to reduce the non-factual responses. We evaluate GAP on a dialogue-based medication recommendation dataset and further explore its potential in a more difficult scenario, dynamically diagnostic interviewing. Extensive experiments demonstrate its competitive performance when compared with strong baselines.