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-Constrained RAG). Rather than directly copying frequent medications from retrieved patients, PACE-RAG personalizes recommendations by first extracting patient-specific clinical features, retrieving cases around these features, and then refining the final prescription using the patient's current symptoms, active medication history, and focus-specific prescribing tendencies. By analyzing treatment patterns tailored to specific clinical features, PACE-RAG generates patient-specific medication recommendations along with 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 suggest that PACE-RAG is a robust and clinically grounded framework for personalized decision support. Our code is available at: https://github.com/ChaeYoungHuh/PACE-RAG.

翻译：药物推荐需要深入理解个体患者的背景，尤其是对于帕金森病等复杂疾病。虽然大语言模型（LLM）具备广泛的医学知识，但难以捕捉实际处方模式中的细微差别。现有RAG方法同样难以应对这些复杂性，因为基于指南的检索仍过于泛化，而相似患者检索常复制多数模式，未能考虑个体患者的独特临床特征。为弥补这一差距，我们提出PACE-RAG（患者感知上下文与证据约束RAG）。PACE-RAG并非直接复制检索患者中的高频用药，而是通过首先提取患者特定临床特征、围绕这些特征检索病例，然后结合患者当前症状、活跃用药史及焦点特定处方倾向来优化最终处方，从而实现个性化推荐。通过分析针对特定临床特征的治疗模式，PACE-RAG生成患者特定的用药推荐及可解释的临床摘要。在帕金森病队列和MIMIC-IV基准上，使用Llama-3.1-8B和Qwen3-8B评估，PACE-RAG取得了最优性能，F1分数分别达到80.84%和47.22%。这些结果表明，PACE-RAG是一种稳健且基于临床的个性化决策支持框架。我们的代码开源在：https://github.com/ChaeYoungHuh/PACE-RAG。