Multiagent GenAI-Powered Oncology Research with GraphMedAI and Neo4j
summary
GraphMedAI builds a Neo4j knowledge graph enriched by RAG from PubMed and ClinicalTrials.gov, adds embeddings for vector similarity, and runs a multiagent stack (orchestrator, query analyzer, retrieval manager, multi-step reasoning, response generator) to answer concrete requests. A live example asks for 5–10 hospitals for a cancer research consortium and returns ranked experts, institutions, and confidence numbers. Claims include faster patient-to-trial matching and KOL discovery, GDPR-aware handling of sensitive data, and scalable deployment with Neo4j + RAG + embeddings.
AI-written summary · about
chapters (7)
- 0:00Introduction and speakers
- 0:30What is GraphMedAI
- 2:41Healthcare challenges in oncology
- 6:20GraphMedAI platform overview
- 9:07How GraphMedAI accelerates oncology
- 10:36Neo4j knowledge graph and agents
- 14:14Demo and results summary
related talks
36mAgentic GraphRAG: AI’s Logical Edge
15mGraph-Driven Knowledge Retrieval: Neo4j for Healthcare Building Codes
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
21mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
30mAgentic RAG with Knowledge Graphs Explained
30mPerformant GraphRAG Improving Neo4j to Drive Autonomous AI ...
01h 40mKnowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications