Event

Neo4j Live: Medical AI with GraphRAG

April 15, 2025
Event
Neo4j Live: Medical AI with GraphRAG

On April 9, 2025, Michael Banf and Johannes Kuhn from our team joined the Neo4j Live podcast to share how Adiu Health uses GraphRAG to streamline clinical documentation and support smarter medical decisions.

In their talk, they explained how integrating large language models (LLMs) with a Neo4j-powered knowledge graph enables precise, context-rich summaries of doctor consultations. The result? Less time spent on paperwork, and more time focused on patient care.

The session covered:

  • How GraphRAG identifies drug interactions, proposes alternative treatments, and supports structured follow-up
  • The architecture and data modeling behind the solution
  • How Neo4j connects to the broader GenAI workflow

The live discussion offered a behind-the-scenes look into the design of scalable, trustworthy AI systems in the healthcare space.

🎥 Watch the full session here:

At Perelyn, we’re proud to contribute to meaningful, real-world applications of AI — where technical innovation meets real human impact.

Other news

Event

Perelyn at Conf42 Large Language Models 2026

Liliya Imasheva presented a validation pipeline for evaluating AI summaries at Conf42 Large Language Models 2026.

June 18, 2026
Read

Event

Perelyn at IOCMA 2026

At the IOCMA 2026 conference, Perelyn presented our method, which transforms graph data such as supply chains or networks so that AI models can learn more reliably from it, even over long distances.

June 10, 2026
Read

Event

Perelyn at Helmholtz AI Conference 2026

Perelyn presented a method at Helmholtz AI Conference for researching cultural values in Large Language Models, which not only reads the models' responses but directly examines their internal representations.

June 8, 2026
Read

Contact us

Name*
Email*
message*
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Help us improve our website. By “Accept” click, do you agree that we store a cookie on your device to analyse the use of the website. Read our Privacy statement for more information.
Something went wrong. Please try again.