The GraphRAG Manifesto: Unlock Better GenAI Results With Knowledge Graphs | Read Now

Neo4j logo

Nodes2024

Dev Conference by Neo4j

Register for NODES 24

You only need to register once to attend all sessions.

More Patience for Patients: How LLMs and Graphs Enable Doctors to Focus on What They Signed Up For

Session Track: AI

Session Time:

Session description

Documentation and evaluation of doctor-patient consultations bind immense amounts of time; time that would be more valuable spent with patients or doing follow-up research. Luckily, the emergence of language models has brought about levels of textual understanding that are capable of handling even such complex tasks as medical documentation. In this session, you will learn about Adiu Health, an AI for automated consultation summarisation and analysis. Adiu Health combines LLMs with a Neo4j-backed graph database to perform accurate and efficient graph-based retrieval tasks (GraphRAG) that complement consultation summarisations with follow-up analyses, such as putative drug replacements or drug interaction side effects.

Speaker

photo of Michael Banf

Michael Banf

Chief AI Scientist, Perelyn GmbH

Michael Banf, PhD, Chief AI Scientist at Perelyn GmbH fell in love with graphs while using AI to decipher the intricacies of the complex gene regulatory networks in eukaryotic organisms as a Feodor Lynen Postdoctoral Research Fellow at the Carnegie Institution for Science, Stanford. Given his passion for both AI and the Life Sciences, he celebrates the unique opportunities that lie at the intersection of language models and graph datastructures which will enable scientists to drive discovery by interacting with the data in an ever more natural manner.