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.

Harmonization of Disparate Health Data Using Graph Database

Session Track: Graphs

Session Time:

Session description

Collecting and harmonizing disparate health data is difficult. Data is captured and exchanged using multiple standards with varying implementations with different levels of conformity. Locale-specific extensions further complicate the task of creating a usable dataset. We recently completed a project that uses Neo4J to harmonize disparate health data to build normalized datasets and AI models for research. In this session, you will see a disparate data ingestion and harmonization toolset that creates a graph model of health data in a Neo4j database. You will also see how Neo4j data can be used to build research datasets in a common data model (OMOP) and how AI training sets can be created.

Speaker

photo of Burak Serdar

Burak Serdar

CoFounder and Lead Architect, Cloud Privacy Labs

Burak Serdar is one of the co-founders of Cloud Privacy Labs where he works on privacy enhancing technologies and semantic interoperability. He is the author of "Effective Concurrency in Go" from Packt Publishing. Earlier, he worked for Red Hat for more than a decade where he led the development of multiple large scale projects. He is also the author of multiple open-source packages, including an embedded openCypher implementation for Go.