NODES 2025 - EEG Topologies with Neo4j: Interpolation-Driven Graph Learning for Chronic Pain Detection

AlgiSense is developing EEG-based digital biomarkers to objectively detect and monitor chronic pain using graph-based AI. A significant technical challenge in EEG research and development is harmonizing feature data from various electrode configurations across research and consumer-grade devices. In this lightning talk, we will explore how Neo4j enables a dynamic and interoperable graph schema that reconciles these configurations through spatial interpolation and graph-based topology mapping, supporting GNN training and inference even when the data includes missing or sparse channels. We utilize Neo4j’s Cypher to implement a scalable interpolation strategy for sensor data, enabling adaptive learning in edge-to-cloud deployments. We will examine how our approach supports low-resource inference, powers personalized pain assessments, and paves the way for foundational graph models in clinical neuroinformatics. This talk will appeal to developers working on bioinformatics, health tech, edge AI, or real-world applications. Speaker: Zeyno Dodd Resources: Get Started with Aura - https://bit.ly/3LOLrjh Deployment Center - https://bit.ly/4jOelM3 Ground AI Systems and Agents with Neo4j - https://bit.ly/4oVsnyb #nodes2025 #neo4j #graphdatabase #graphrag #knowledgegraph