MedPlan introduces an innovative two-stage system that mimics clinicians' reasoning process to generate personalized medical treatment plans from electronic health records.

• Implements a sequential approach that separates assessment from treatment planning, mirroring clinical workflows
• Incorporates patient-specific historical context for more relevant and personalized treatment recommendations
• Effectively distinguishes between subjective and objective clinical information for improved treatment planning
• Utilizes Retrieval-Augmented Generation (RAG) to enhance accuracy and reliability

This research addresses a critical gap in healthcare AI by moving beyond diagnosis to actionable treatment plans, potentially improving clinical decision-making and patient outcomes while maintaining the natural workflow of healthcare providers.

MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation