Skip to content

Graph RAG

Evaluating GraphRAG vs. RAG on Real-World Messages

📚 View all posts in the Graph-based Healthcare Series

Graph-based Healthcare Series — 6

This is the sixth post in our ongoing series on graph-based healthcare tools. Stay tuned for upcoming entries on clinical modeling, decision support systems, and graph-powered AI assistants.

In our previous post, we introduced a Bayesian diagnostic engine that uses synthetic patient data to quantify clinical evidence, score conditions, and update probabilities in a way that mirrors how clinicians think.

In this post, we zoom out from system architecture and generative modeling to answer a practical question:

How does GraphRAG perform on real patient messages compared to a traditional RAG system?

To evaluate this, we tested both systems on real-world caregiver messages from Last Mile Health (LMH), labeled and scored by GPT-4o, across over 300 cases. The results provide a compelling look at the strengths, weaknesses, and tradeoffs of graph-structured retrieval in clinical QA tasks.

Bayesian Pattern Recognition for Real World Applications

📚 View all posts in the Graph-based Healthcare Series

Graph-based Healthcare Series — 5

This is the fifth post in an ongoing series on graph-based healthcare tools. Stay tuned for upcoming entries on clinical modeling, decision support systems, and graph-powered AI assistants.

In our previous post, we explored how large language models (LLMs) can simulate realistic pediatric patient encounters based on the IMNCI guidelines. These synthetic notes were grounded in real clinical logic, labeled with structured IMNCI classifications, and validated using a multi-agent verification strategy inspired by the Bayesian Truth Serum (BTS). The result: a high-fidelity dataset of richly annotated, clinically plausible pediatric cases.

In this post, we put that dataset to work—prototyping a Bayesian diagnostic engine that quantifies clinical evidence, scores conditions, and updates probabilities in a way that mirrors how clinicians think.

Enhancing Patient Diagnosis with Graph-based Retrieval-Augmented Generation

📚 View all posts in the Graph-based Healthcare Series

Graph-based Healthcare Series — 2

This is the second post in an ongoing series on graph-based healthcare tools. Stay tuned for upcoming entries on clinical modeling, decision support systems, and graph-powered AI assistants.

In our previous post, we explored how the Integrated Management of Neonatal and Childhood Illness (IMNCI) guidelines were transformed from static, text-heavy documents into an interactive graph model. This structure enabled more intuitive navigation of clinical logic, laying the groundwork for advanced applications in AI-assisted patient diagnosis.

In this follow-up, we demonstrate how that graph model serves as the foundation for a graph-based retrieval-augmented generation (graph RAG) system. By combining the structured clinical knowledge encoded in Neo4j with the generative capabilities of large language models (LLMs), we create a framework that supports transparent, context-aware patient diagnosis at the point of care.