PACE-RAG: Patient-Aware Contextual and Evidence-based Policy RAG for Clinical Drug Recommendation

2026-03-18

AI Summary

Existing drug recommendation methods struggle to simultaneously account for individualized patient clinical characteristics and real-world prescribing patterns, often resulting in recommendations that lack both precision and interpretability. To address this limitation, this work proposes the PACE-RAG framework, which innovatively integrates patient-specific contextual information with evidence-driven prescribing strategies derived from similar cases. This approach overcomes the conventional trade-off in retrieval-augmented generation (RAG) systems—where strong generalization in clinical decision-making typically comes at the expense of personalization. Leveraging large language models Llama-3.1-8B and Qwen3-8B, PACE-RAG achieves F1 scores of 80.84% on a Parkinson’s disease cohort and 47.22% on the MIMIC-IV dataset, significantly outperforming current state-of-the-art methods and enabling context-aware, interpretable, and personalized drug recommendations.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Drug recommendation requires a deep understanding of individual patient context, especially for complex conditions like Parkinson's disease. While LLMs possess broad medical knowledge, they fail to capture the subtle nuances of actual prescribing patterns. Existing RAG methods also struggle with these complexities because guideline-based retrieval remains too generic and similar-patient retrieval often replicates majority patterns without accounting for the unique clinical nuances of individual patients. To bridge this gap, we propose PACE-RAG (Patient-Aware Contextual and Evidence-based Policy RAG), a novel framework designed to synthesize individual patient context with the prescribing tendencies of similar cases. By analyzing treatment patterns tailored to specific clinical signals, PACE-RAG identifies optimal prescriptions and generates an explainable clinical summary. Evaluated on a Parkinson's cohort and the MIMIC-IV benchmark using Llama-3.1-8B and Qwen3-8B, PACE-RAG achieved state-of-the-art performance, reaching F1 scores of 80.84% and 47.22%, respectively. These results validate PACE-RAG as a robust, clinically grounded solution for personalized decision support. Our code is available at: https://github.com/ChaeYoungHuh/PACE-RAG.

Problem

• drug recommendation
• patient context
• personalized medicine
• clinical decision support
• Parkinson's disease

Innovation

• Patient-Aware RAG
• Evidence-based Policy
• Clinical Drug Recommendation
• Personalized Decision Support
• Prescribing Pattern Analysis