Why should you participate in this online training?
- You will learn the basics of AI / ML and its applicability in the GxP Environment
- How can pharmaceutical basics, e.g. risk management and qualification / validation be applied to AI? You will experience first approaches!
- Are relevant pharmaceutical regulations adapted to this new technology and what expectations does an inspector have during an inspection? First concepts will be presented!
- In case studies, pharmaceutical companies show first practical and practised approaches to the use of AI
At the latest, artificial intelligence (AI) has arrived in the General public since ChatGPT and Bard. Opinions range between absolute euphoria and the invocation of the downfall of humanity. The foundations of AI were laid many years ago and can now be widely implemented due to massively available computing power. The topic has also found its way into the pharmaceutical landscape. First applications have come into operation. The interesting questions here are whether and how this technology is compatible with pharmaceutical regulations, specifications and authorities’ expectations.
The Online Training is aimed at managers and QA members as well as engineers from the pharmaceutical industry, suppliers and service companies who qualify and operate AI applications in a GxP environment.
To participate in an on demand training course or webinar, you do not need any software. The recordings are made available via a streaming server. In general, the recording is provided in MP4 format, which any PC (Microsoft Windows, Apple IOS) or tablet can easily display.
Timing and Duration:
When you register for the on demand Training course or webinar you can decide at what date you want to follow the training course online. For a 1-day training course you will have 2 days in which the stream is available (for 2-day training course 3 days and for a 3-day training course 4 days). Within in this timeframe you can start & stop the stream according to your needs.
In time before the scheduled date (your desired date) you will receive an e-mail from us with a link for direct participation as well as your log-in data.
Training Course Documentation and Certificate:
The presentation will be made available as PDF-files via download during the online training course. After the successful completion of the online training, you are able to download the certificate of attendance.
Regulatory Requirements / Concerns
Dr Arno Terhechte
- Pharmaceutical laws (AMG and other)
- EU-GMP Guide Annex 11
- Concept Paper Revision of Annex 11
- Software as Medical Device
Validation Approaches
Stefan Münch / Yves Samson
- Maturity: Increasing autonomy and transferring Control
- Governance: Developing and operating AI solutions in GxP-regulated areas
Risk Management
Stefan Münch / Yves Samson
- Power with control: Explaining the outcomes of trained models
- Applying QRM to development and operation of AI applications
Regulatory Requirements / Assessment
Dr Arno Terhechte
- Inspection strategy
- What do inspectors expect from the regulated user?
Case Study: Predictive Control of Yield & Titer
Dr Hadj Latreche
- Apply Advanced Analytics to enable predictive Titer/Yield and reduce variability while increasing mean toward high-end value
- In-Flight predictive and adaptive process oversight for shop floor to target Titer/Yield Golden Batches
- Prove the value of utilizing Advanced Analytics as a digital product leveraging different data sources and advanced predictive algorithms
- Build site future capabilities required for a sustainable way of working using Advanced Analytics
Case Study: AI in Medical Device Area
Christophe Girardey
- Introduction on the regulations in Medical Device area
- AI in Medical Device:
- Patient risk: more direct than in Pharma?
- Reality not future: FDA list of devices released.
- Guidelines on AI:
- (FDA GMLP > optional as already covered in one of the other sessions)
- AI & Cybersecurity (ENISA guideline)
- NMPA Guideline on AI
- Examples of a use case:
- Electrocardiogram analysis with AI
Case Study: Revolutionizing Visual Inspection with Artificial Intelligence
Dr Mario Holl
- Pain points in visual inspection
- A machine-agnostic AI solution Framework
- Strategies for developing robust and reliable AI models
- Qualification and necessary documentation
- Results of AI powered visual inspection
Case Study: Challenges and Limitations of Machine Learning Systems in Automated Visual Inspection Systems
Haluk Dönmez
- Introduction and Basics
- Application and Challenges
- Approach and ML Training
- Testing and Qualification
- Conclusion
Enhancing Production Efficiency: An End-to-End Process Perspective through Data Science
Julius Kittler / Thomas Singer
- Introduction and Overview of the Use Case
- Consolidating the Tablet Production Process into a Comprehensive Dataset
- Theoretical Basics of Machine Learning and Gradient Boosting Decision Trees
- Application of Machine Learning to Identify Critical Factors Impacting Production Target Variables
- Key Takeaways and Lessons Learned
Recording from 10 October 2023
Duration of Recording: approx. 5:01 h