Case Study: Boston Scientific achieves rapid root-cause supply chain analysis and faster quality control with Neo4j

Graph Data Science Streamlines Complex Medical Supply Chain Analysi

Boston Scientific, a global medical device maker, faced a growing challenge: its highly vertical, batch-and-discrete manufacturing process produces complex devices from many parts, and distributed engineering teams were relying on decentralized spreadsheets for analysis. That ad-hoc approach led to inconsistencies and an inability to reliably trace root causes of quality issues across the supply chain, so the company needed a more effective, scalable method to analyze and coordinate manufacturing data.

The team adopted Neo4j AuraDB Enterprise, modeling finished products, parts, and issues as a graph and applying Graph Data Science algorithms and Cypher queries (including Shortest Path and proximity scoring) to surface relationships and rank failure-prone components. The approach enabled rapid root-cause identification, reduced analytical query times from about two minutes to 10–55 seconds, improved cross-team understanding with a simple shared model, and scaled via a fully managed cloud deployment so analysts can focus on quality insights.

Boston Scientific

Eric Wespi

Data Scientist