Do More with Less: Create the Most Informative Data with a Minimal Effort!
Research and Development in pharma/biopharma means:
- Most data still has to be created.
- Creating data is costly.
Why does the industry not optimize the return on this data investment?
It is clear that sub-optimal data in R&D would lead to inferior products or processes both in terms of quality and performance and therefore would have a substantial financial impact. The science of systematically creating the most informative data at the minimal possible cost is design of experiments (DOE). It has been embraced by the industry where it is a regulatory requirement, but its vast overall potential – comparable to that of big data/AI – has been largely untapped.
Moreover, if you think that the big data/AI revolution is more interesting and has made DOE obsolete – think again! Deep learning can only exploit information that is actually in the data and it requires thousands of training examples, i.e. batches or experiments (irrespective of how much data you have for each)! So for a lot of your development tasks, it will just never be applicable. Irrespective of how we are going to analyze the data, design of experiments enables us to create the maximum amount of good information with a minimal effort!
But hasn’t that been around for a long time?
DOE has silently been used successfully in many industries for decades, enabling its proponents to achieve substantial improvements and to outclass their competition. Likewise, the most well-known DOE approaches have been around for a long time, but recent years have seen important advances which make its use much more efficient and simpler for a general audience. Overall, there is currently a substantial lack of relevant DOE expertise and an incredible untapped potential for modern DOE in the pharmaceutical and biopharmaceutical industry.
Why this course?
The majority of DOE trainings waste your precious time on outdated, inefficient designs and plenty of cumbersome theory which does not contribute to you acquiring a working knowledge. This course brings you from a beginner or intermediate level in the shortest amount of time possible to become a confident expert. You obtain the essential understanding and knowledge for what you will actually do in practice. Everything is backed up by practical exercises on pharmaceutical/biopharmaceutical problems / data in the Design Expert software, which is the best overall software for DOE practitioners. Training licenses for Design Expert are provided if needed.
Who can benefit from this course?
This course is aimed at practitioners in the pharma/biopharma industry who want to use DOE for their own projects or want to become local experts in DOE. Some rudimentary prior knowledge would be advantageous but is not necessary. The course does not contain any equations, but still provides a solid basis for becoming a qualified DOE specialist and covers all aspects required in a pharmaceutical setting. Also, dozens of statisticians have benefited from it by being provided with a comprehensive insight and efficient workflow for deploying DOE in practice.
Your Trainer
Dr. Jürgen von Frese has 25 years of experience in industrial data analysis and has worked as a DOE expert in pharma/biopharma for over 10 years. He has provided decisive contributions to shaping the DOE strategy at one of Europe’s major biopharmaceutical companies and this course has been a key element in that strategy. Well over 100 trainees have successfully completed it and have contributed to its continuous improvement.
Modules
Module 1: Developing a Design
November 6th to 9th, 2023 / 14 – 18 CET (Europe) / 8 – 12 EST (US)
- Principles of DOE
- The Workflow for Establishing a Designed Experiment
- Different Design Types
- Evaluating the Suitability of Designs
The focus is on getting a conceptual understanding on where and how to use design of experiments (DOE) and how to obtain the best and most efficient designs.
1595 €
Module 2: Analyzing DOE Data
November 13th to 16th, 2023 / 14 – 18 CET (Europe) / 8 – 12 EST (US)
- Principles for Obtaining Valid Models
- The Workflow for Analyzing DOE Data
- What can we learn from DOE models?
- Establishing Design Spaces
This course provides a step-by-step understanding on how to analyze DOE data by systematically building a valid model, how to evaluate the quality of an obtained model and how to draw conclusions from that model. As a specific application in the pharmaceutical setting the development of a design space is discussed.
1595 €
Add-on Module Formulation / Mixture Design
November 21st and 23rd, 2023 / 14 – 18 CET (Europe) / 8 – 12 EST (US)
Whenever our experiments involve ingredients/components for which only relative amounts (%) matter, e.g., in a typical formulation setting, this requires very particular experimental designs and analysis approaches also known as mixture designs. This add-on module enables its participants to understand the relevant principles and methods, enabling them to design and successfully analyze mixture designs (as well as those including additional process factors).
795 €
Add-on Module Robust Parameter Design
November 28th 2023 / 14 – 18 CET (Europe) / 8 – 12 EST (US)
When using DOE, we generally focus on the predicted means of our responses and try to optimize them according to our needs. But it is also possible to consider and minimize the future variability of the responses. Corresponding approaches have initially been introduced by G. Taguchi into the quality culture, but more powerful methods are available now. This course is an add-on module and will enable its participants to understand the principles for designing and analyzing robust parameter designs and thereby optimizing CQAs and KPIs while simultaneously minimizing their variability.
395 €
Registration
Data Analysis Solutions SLU
Carrer de la Costa 29
07589 Capdepera / Spain
www.da-sol.com /