Clinical data in hospitals span multiple modalities and platforms, making information retrieval inefficient for medical professionals. This project presents an agentic clinical RAG system that autonomously coordinates specialized modules for structured EHR data, unstructured clinical notes, and multimodal imaging. Unlike fixed-sequence Generative AI workflows, the agentic workflow performs dynamic reasoning and task planning such as interpreting clinician’s query, determines which sources EHR records, narrative notes, or imaging are required, and delegates tasks to the appropriate agents. Each agent applies its specialized RAG pipeline and exchanges intermediate context with others through an Agent-to-Agent (A2A) communication framework within the Model Context Protocol (MCP) environment, enabling a unified and clinically grounded response. This architecture supports intelligent retrieval, reduces redundancy 11 across systems, and enhances workflow efficiency. Experimental results show improved traceability, interpretability, and reliability in clinical outputs, advancing the development of safe and scalable AI assistants for healthcare decision support.
Watch the team present this project at 01:28:24 in the session recording here.
Keywords: Clinical RAG, GraphRAG, Agentic RAG, large language models (LLMs), knowledge graphs, healthcare AI, retrieval-augmented generation, multi-agent systems, model context protocol (MCP), Agent2Agent (A2A), multimodal data integration
Faculty Advisor
Dr. Pamuksuz, a professor of AI, specializes in applied mathematics, machine/deep learning, responsible and generative AI. He has contributed to various analytics journals, including IEEE Transactions on Artificial Intelligence, and has shared his insights at several national and international conferences.
Since joining the University of Chicago as a faculty member in 2018, Dr. Pamuksuz has taught a range of subjects, including data mining, machine learning, and linear & non-linear models, along with more specialized areas like AI-data science for leaders and Generative AI Research. His supervision of capstone theses has often centered on computer vision and natural language processing.
In the professional realm, Dr. Pamuksuz has an impressive record. He has led data science teams at several Fortune 500 companies, provided expert consultancy in architecting cloud-based machine learning solutions, and co-founded Inference Analytics in 2018. Under his leadership, Inference Analytics was recognized in 2023 as one of the top Machine Learning Companies in Illinois, marking a significant milestone in healthcare analytics in Chicago.
Dr. Pamuksuz’s academic path has taken him through some of Illinois’ most prestigious universities. He completed his MS in Computer Engineering/Science at Northwestern University and went on to earn his Ph.D. from UIUC. Today, he contributes his expertise as a faculty member at the University of Chicago. This journey, connecting three significant academic institutions, reflects a strong foundation and dedication to his field and a deep engagement with the state’s rich educational landscape. Outside of his professional endeavors, Dr. Pamuksuz is enthusiastic about hackathons, not only participating in several but also organizing them twice annually since 2020. His involvement has yielded notable success in various data challenges. As a sports fan, he follows Champions League Soccer, supporting Galatasaray, and enjoys engaging in basketball and volleyball during his leisure time. He also enjoys smooth/gypsy jazz where you can find him on Wednesdays in his favorite place Green Mill.