PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation
Researchers have developed PACE-RAG, a novel retrieval-augmented generation framework designed to improve drug recommendations for patients with complex conditions like Parkinson's disease. Unlike existing methods that either use generic guidelines or replicate common treatment patterns, PACE-RAG personalizes recommendations by extracting patient-specific clinical features. It then refines prescriptions based on current symptoms, active medications, and specific prescribing tendencies, providing an explainable clinical summary. Evaluated on the MIMIC-IV benchmark using Llama 3.1:8b and Qwen3 8B models, PACE-RAG achieved state-of-the-art F1 scores, demonstrating its robustness for clinical decision support. AI
IMPACT Enhances clinical decision support by providing more personalized and explainable drug recommendations for complex patient cases.