Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yichi Zhu, Kan Ling, Xu Liu, Hengrun Zhang, Huiqun Yu, Guisheng Fan

TL;DR

Experimental results demonstrate robust knowledge extraction capabilities and show promises of using PharmGraph-Auditor to enable pharmacists to achieve safer and faster 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.

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

TL;DR

Experimental results demonstrate robust knowledge extraction capabilities and show promises of using PharmGraph-Auditor to enable pharmacists to achieve safer and faster 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.
Paper Structure (31 sections, 7 figures, 5 tables, 1 algorithm)

This paper contains 31 sections, 7 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Methodology
  3. Theoretical Foundation: Hybrid VKG Model
  4. Set Constraint Satisfaction (Why Relational?)
  5. Topological Traversal (Why Graph?)
  6. Trustworthy HPKB Construction
  7. Phase I: Iterative Schema Refinement (ISR)
  8. Stratified Sampling Strategy.
  9. Human-AI Synergy: Gap Detection and Abstraction.
  10. Decision Policy and Stabilization.
  11. Phase II: Section-Aware Knowledge Population
  12. 1. Document Preprocessing and Sectioning
  13. 2. The Section-Aware Multi-Agent Framework
  14. 3. Hybrid Persistence and Mapping Layer
  15. KB-Grounded Prescription Auditing
  16. ...and 16 more sections

Figures (7)

  • Figure 1: The workflow and the role of PharmGraph-Auditor.
  • Figure 2: System architecture of PharmGraph-Auditor.
  • Figure 3: The KB-grounded Chain of Verification (CoV) framework.
  • Figure 4: The Patient Profile-driven Evidence Selection Tree (P-EST) logic for pruning conflicting dosage rules.
  • Figure 5: Types of prescription errors.
  • ...and 2 more figures