A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification

TL;DR

This paper presents PharmGraph-Auditor, a hybrid knowledge-based system that enhances safety and traceability in prescription verification by integrating a trustworthy knowledge base with a novel reasoning paradigm, addressing LLM limitations.

Contribution

The paper introduces a new hybrid framework combining a Virtual Knowledge Graph and a co-evolved schema for safe prescription auditing, with a novel reasoning method for transparency.

Findings

Robust knowledge extraction from medical texts.

Effective hybrid query plans for evidence retrieval.

Improved speed and safety in prescription verification.

Abstract

Medication errors pose a significant threat to patient safety, making pharmacist verification (PV) a critical, yet heavily burdened, final safeguard. The direct application of Large Language Models (LLMs) to this zero-tolerance domain is untenable due to their inherent factual unreliability, lack of traceability, and weakness in complex reasoning. To address these challenges, we introduce PharmGraph-Auditor, a novel system designed for safe and evidence-grounded prescription auditing. The core of our system is a trustworthy Hybrid Pharmaceutical Knowledge Base (HPKB), implemented under the Virtual Knowledge Graph (VKG) paradigm. This architecture strategically unifies a relational component for set constraint satisfaction and a graph component for topological reasoning via a rigorous mapping layer. To construct this HPKB, we propose the Iterative Schema Refinement (ISR) algorithm, a framework that enables the co-evolution of both graph and relational schemas from medical texts. For auditing, we introduce the KB-grounded Chain of Verification (CoV), a new reasoning paradigm that transforms the LLM from an unreliable generator into a transparent reasoning engine. CoV decomposes the audit task into a sequence of verifiable queries against the HPKB, generating hybrid query plans to retrieve evidence from the most appropriate data store. Experimental results demonstrate robust knowledge extraction capabilities and show promises of using PharmGraph-Auditor to enable pharmacists to achieve safer and faster prescription verification.