Insight

The AI-enabled digital twin for life sciences

An Artificial Intelligence (AI) enabled digital twin is a state-of-the-art simulation of a complex real-world system, enhancing predictive AI

Bill Nowacki

Bill Nowacki

Managing Director, Data & Analytics, KPMG US

+1 224-848-9237

Kerim Ozbilge

Kerim Ozbilge

Advisory Managing Director, Supply Chain & Operations, KPMG US

+1 312-665-2337

An Artificial Intelligence (AI) enabled digital twin is a state-of-the-art simulation of a complex real-world system, enhanced with predictive AI. It has the capability to tap into a data stream, learn, and run “alongside and ahead of” increasingly complex highly interconnected real-world manufacturing and asset management system and provide the ability to identify areas for improvement, model improvement scenarios, provide tactical decision support for unexpected challenges, as well as model and optimize systems during design to avoid costly changes later during implementation.

Digital twins continue to evolve quickly and gain traction as an important problem-solving tool in life sciences driven by advances in AI, cloud computing, Internet of things, and simulation by blending the relative strengths of these component technologies. Digital twins have found application in life sciences research & development (R&D), process, manufacturing, supply chain, intelligent medical devices, advanced diagnosis and therapy, business and new product introduction modeling, and logistics.

Client challenge

A leading global bio pharma company was experiencing challenges meeting demand for one of their mainstay products, which was impacting commitments as a trusted supplier for their providers and patients that counted on them, as well as their financial performance. Many difficult-to-model factors were potentially affecting the steps in the supply chain, ranging from environmental, to labor and biochemical, and they were struggling to understand, prioritize, and operationalize avenues for performance improvement in the areas of lead times, service levels and cost-to-produce.