Digital Twin Technology in pharmaceutical industries

Digital Twin technology has transformative potential in the pharmaceutical industry, enhancing efficiency, quality, and innovation.

What is Digital Twin technology?

Digital Twin is a virtual replica of a physical asset, process, or system, simulated in real-time using data and analytics.


Applications in Pharma:

1. Manufacturing Optimization: Virtual replicas of production lines and equipment enable simulation, prediction, and optimization of manufacturing processes.
2. Quality Control: Digital Twins monitor and analyze production parameters, detecting potential quality issues before they occur.
3. Supply Chain Management: Virtual modeling of supply chains improves forecasting, logistics, and inventory management.
4. Product Development: Digital Twins simulate clinical trials, formulation, and packaging, reducing time-to-market and costs.
5. Regulatory Compliance: Virtual audits and inspections ensure compliance with regulatory requirements.
6. Predictive Maintenance: Digital Twins anticipate equipment failures, reducing downtime and increasing overall equipment effectiveness.


Benefits:

1. Increased efficiency
2. Improved product quality
3. Reduced costs
4. Enhanced innovation
5. Better regulatory compliance
6. Real-time decision-making


Pharma Companies adopting Digital Twin:

1. Pfizer
2. Novartis
3. GlaxoSmithKline
4. Sanofi
5. Johnson & Johnson


Technologies enabling Digital Twin:

1. Internet of Things (IoT)
2. Artificial Intelligence (AI)
3. Machine Learning (ML)
4. Cloud Computing
5. Data Analytics


Challenges:

1. Data integration and standardization
2. Cybersecurity concerns
3. Regulatory frameworks
4. Talent acquisition and training
5. Scalability and interoperability


Future Outlook:

Digital Twin technology will continue to transform the pharmaceutical industry, driving innovation, efficiency, and quality. As the technology advances, we can expect:


1. Increased adoption
2. Integration with emerging technologies (e.g., blockchain, AR/VR)
3. Improved data analytics and AI capabilities
4. Enhanced collaboration and knowledge-sharing

1. An Overview of Digital Twin Technology in Pharmaceutical Industry. University Department of Chemical Technology Guided by :- Dr. S.G. Vaishnav PRESENTED BY :- CHOURE KRISHNAKANT AJIT ROLL NO. :- MPQA 002004 (Pharmaceutical Quality Assurance Department) 1

2. DEFINITION Digital twin technology creates a virtual replica of a physical pharmaceutical manufacturing process, allowing for simulation, prediction and optimization. BENEFITS: Increased Efficiency: Reduced production downtime and improved yield. Cost Savings: Minimized waste, energy consumption, and maintenance costs. Improved Quality: Enhanced product consistency and reduced defects. Regulatory Compliance: Simplified audits and compliance with regulatory requirements. Innovation: Faster development of new products and processes. 2

3. INTRODUCTION History : Digital Twin concept originated in 2002 by Dr. Michael Grieves applications in aerospace and defense industries Expanded to various sectors, including pharmaceuticals, healthcare, manufacturing, and infrastructure. Key Components: Physical Entity: Real-world system, process, or product Virtual Model: Digital representation of the physical entity Data Integration: Real-time data exchange between physical and virtual entities Analytics and Simulation: Predictive analytics and simulation capabilities ‹#›

4. Fig :- Physical component, virtual component, and data management platform of a general digital twin (DT) framework ‹#›

5. LEVELS OF DIGITAL TWIN Descriptive twin : The descriptive twin is a live, editable version of design and construction data visual replica of a built asset. (Users specify) Informative twin :This level has an added layer of operational and sensory data. Predictive twin :This twin can use operational data to gain insights. Comprehensive twin :This twin simulates future scenarios and considers “what-if” questions. Autonomous twin :This twin has the ability to learn and act on behalf of users. 5

6. Type of Digital Twinning Parts Twinning : Virtual representation of individual components , Analyzes physical, mechanical, and electrical characteristics. Examples: CAD/CAM, electronic circuit simulation 2. Product Twinning : Twinning interoperability of parts, Optimizes constituent parts for better performance, Reduces mean time between failures (MTBF) and mean time to repair (MTTR) System Twinning : Monitors and optimizes entire systems , Enables real-time monitoring and experimentation Examples: energy grids, communication systems, industrial manufacturing 6

7. Digital Twin Technologies include Artificial Intelligence (AI): Machine learning and deep learning. Internet of Things ( IoT ): Real-time data integration. Cloud Computing: Scalable infrastructure. 3D Modeling : Virtual representation of equipment and processes. Simulation Software: Tools like ASPEN Plus, COMSOL, and ANSYS. Tools and its uses 1. ANSYS: Simulation-driven design for product development. 2. COMSOL: Multiphysics simulation for process optimization. 3. ASPEN Plus: Process simulation for chemical and pharmaceutical industries. 4. Dassault System : 3D modeling and simulation for product design. 5. Siemens NX: Integrated CAD, CAE, and CAM for product development . 7

8. APPLICATIONS 1 . Process Simulation: Modeling and analysis of pharmaceutical processes. 2. Equipment Optimization: Virtual testing and optimization of equipment performance. 3. Supply Chain Management: Simulation of supply chain dynamics. 4. Quality Control: Predictive modeling of quality attributes. 5. Operator Training: Virtual training environments. 8

9. 9 Fig : The trend of publications on digital twins from 2016 to the end of November 2023 .

10. CHALLENGES AND LIMITATIONS 1. Data Quality: Accurate and reliable data integration. 2. Scalability: Handling complex processes and large datasets. 3.Security : Protecting sensitive data. 4. Regulatory Frameworks: Evolving regulatory requirements. 10

11. Case Study 1: Pharmaceutical Supply Chains Focus: Patient performance and inventory optimization. Example: Just-in-Time clinical pharmacy improves drug trial efficiency and reduces waste. Technologies: Continuous manufacturing with predictive models and smart packaging (track and monitor drugs) 2 : Simulation of the Blockchain-Enabled Digital Twin Simulation Setup: A pilot trial was simulated using Hyperledger Fabric technology to assess the bioavailability of a generic drug. A system of six interconnected servers facilitated real-time monitoring . Key Results: DT identified critical safety issues, which were overlooked in the real-life trial, by continuously assessing factors like blood pressure and heart rate before and after drug administration . Outcome: The system efficiently detected participants at risk and developed safety control strategies for future trials. 11

12. Best practice digital twin approach for pharma equipment qualification Identify equipment and requirements:   Identify the pharmaceutical equipment to be qualified list the regulatory requirements and standards that need to be met. Data collection and model creation:   Gather relevant design and operational data for the equipment create a digital twin model using the collected data. Calibration and validation:  Calibrate the digital twin model to ensure it accurately represents the real equipment validate the digital twin’s performance against historical data and real-world measurements. Simulation and testing:  Use the calibrated digital twin to conduct virtual simulations and tests evaluate the equipment’s performance under different scenarios and conditions. Deviation analysis:   Optimization and adjustment:   Verification and approval:   Ongoing monitoring and maintenance:   Equipment qualification report: Continuous improvement: 12

13. 3D: three-dimensional; AI: artificial intelligence; CRT: Cardiac resynchronisation therapy; CT: computed tomography; DT: digital twin; FEM: finite element method; GPU: graphics processing unit; IK: inverse kinematics; IoT: internet of things. Table 1. Representative applications of DT in medical fields . 13

14. Conclusion: By creating virtual replicas of physical systems, processes, and products, digital twins enable pharma companies to simulate, predict, and optimize various aspects of their operations. The adoption of digital twin technology has help to: Improved productivity and efficiency Enhanced product quality and reliability Reduced time-to-market for new medicines Increased supply chain flexibility Better data-driven decision-making Enhanced regulatory compliance 14

15. Reference : 1) MD. DOULOTUZZAMAN XAMES , (Member, IEEE), AND TAYLAN G. TOPCU Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA 24061, USA A Systematic Literature Review of Digital Twin Research for Healthcare Systems: Research Trends, Gaps, and Realization Challenges Received 7 December 2023, accepted 31 December 2023, date of publication 3 January 2024, date of current version 10 January 2024. Digital Object Identifier 10.1109/ACCESS.2023.3349379 2) Xiaoyang Zhu  Zhejiang University Yangjian Ji  A Digital Twin-Driven Method for Online Quality Control in Process Industry DOI: https://doi.org/10.21203/rs.3.rs-571586/v1 3) Evangelia Katsoulakis1,2, Qi Wang3 , Huanmei Wu4 , Leili Shahriyari 5 , Richard Fletcher6,7, Jinwei Liu 8 , Luke Achenie9 , Hongfang Liu10, Pamela Jackson11, Ying Xiao12, Tanveer Syeda-Mahmood13, Richard Tuli2 & Jun Deng Digital twins for health: a scoping review npj digital medicine Review article Published in partnership with Seoul National University Bundang Hospital https://doi.org/10.1038/s41746-024-01073-0 4) Tianze Sun1,2,*, Xiwang He3,* and Zhonghai Li1,2 Digital twin in healthcare: Recent updates and challenges Digital Health Volume 9: 1–13 © The Author(s) 2023 Article reuse guidelines: sagepub.com/journals-permissions DOI: 10.1177/20552076221149651 journals.sagepub.com/home/ dhj 5) Jagjit Singh Srai * , Ettore Settanni, Naoum Tsolakis, Parminder Kaur Aulakh Supply Chain Digital Twins: Opportunities and Challenges Beyond the Hype 23rd Cambridge International Manufacturing Symposium University of Cambridge, 26 – 27 September 2019 6) Reza Vatankhah Barenji * and Reza Ebrahimi Hariry Blockchain-Enabled Quality Improvement Digital Twin for Clinical Trials doi : 10.20944/preprints202305.1693.v1 Preprints ( www.preprints.org ) 7) Tiago Coito (Corresponding Author)a IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal IDMEC, Instituto Superior Técnico, Assessing the impact of automation in pharmaceutical quality control labs using a digital twin Version of Record: https://www.sciencedirect.com/science/article/pii/S0278612521002442 Manuscript_9065a9c794a31bc21ad9b100f196de8f 8) https://atos.net/en/industries/healthcare-life-sciences/pharma-digital-twin 9) https://www.pharmamanufacturing.com/quality-risk/article/33011285/modernizing-equipment-qualification 10) https://www.linkedin.com/pulse/digital-twin-healthcare-precious-chisom-uzoeghelu-1yfge?utm_source=share&utm_medium=member_android&utm_campaign=share_via 15

16. Thank you . 16