Digital Twin: Data Science Engine
In collaboration with
This project aims to address critical gaps in data analysis and predictive modeling by employing advanced mathematical models and machine learning techniques for healthcare applications. A key objective is to develop a predictive engine based on these methodologies, ensuring higher accuracy and reliability in forecasting and trend analysis. The approach integrates cutting-edge optimization strategies to improve efficiency and effectiveness in complex systems. CERN will contribute its expertise in Digital Twin technology and advanced methodologies developed in the context of high-energy physics experiments.
Overview
This project aims to address critical gaps in data analysis and predictive modeling by employing advanced mathematical models and machine learning techniques for healthcare applications. A key objective is to develop a predictive engine based on these methodologies, ensuring higher accuracy and reliability in forecasting and trend analysis. The approach integrates cutting-edge optimization strategies to improve efficiency and effectiveness in complex systems. CERN will contribute its expertise in Digital Twin technology and advanced methodologies developed in the context of high-energy physics experiments.
Highlights in 2025
In 2025, the project focused on strengthening collaboration and alignment between CERN and Johnson & Johnson. A series of dedicated meetings were held both at CERN and at Johnson & Johnson’s offices in Basel, providing valuable opportunities to refine the shared vision, exchange expertise, and align expectations across scientific, technical, and organisational perspectives. These interactions helped consolidate the partnership, clarify priorities, and lay the groundwork for future technical activities by reinforcing mutual understanding and long-term collaboration.
Next Steps
Building on the strengthened collaboration established in 2025, the next phase of the project will focus on translating the shared vision into concrete technical activities. This includes identifying priority use cases, refining technical requirements, and exploring suitable data, models, and computing approaches to support the development of the Digital Twin Data Science Engine. These steps will prepare the ground for future implementation and experimentation.
Publications & Presentations
Mu, G. (2025, March 5). Digital Twin – Data Science Engine [Conference presentation]. 2025 CERN openlab Technical Workshop, Meyrin, Switzerland.
Technical Team
Nicola Serra, Sara Sansaloni Pastor, Victorien Leconte
Project Coordinator
Nicola Serra
Collaboration Liaisons
Gang Mu