Digital Thread and Analytics Model to Improve Quality Controls in Surgical Stapler

Abstract

Ethicon, Inc. currently collects data in various stages of its supply chain, but the information is fragmented across the end-to-end chain, resulting in a reactive supply chain. This study seeks to understand the data maturity of Ethicon's surgical stapler through exploratory data analysis and experimental data modeling with machine learning techniques in order to provide recommendations on strategies for digital readiness in a medical device and outline potential opportunities digitization can bring.

The goals of this project are: 1. Enable end-to-end visibility into the currently supply chain by building a digital thread for a surgical stapler product 2. Create visualizations to provide visibility and insight into the existing production process 3. Use advanced analytics models to identify key components or measurements that affect the product's Force to Fire final quality inspection results

The digital thread and models built laid the groundwork for the Ethicon team to understand the current state of their systems and will be used as the team conducts experiments to further understand the actual devices being built.