Accelerate Value-Based Drug Development Using Real World Data and Predictive Analytics

Value-based drug development refers to the pharmaceutical and device producers striving to create value for patients and health systems with new therapies. There is an increasing need to maximize usage of real world data (as well as RCT data) along with predictive analytics so that development program planning and execution can be achieved with maximum efficiency.

Learn how the following industry hot topics are all part of the value-based drug development ecosystem:

• Model-based drug development
• Risk-based monitoring
• Market access
• Health economics & outcomes research
• Real-world data and evidence

From a data and analytics perspective, accelerating value-based drug development means having an analytics ecosystem where access to data is readily available and where analytics (including predictive analytics) are democratized appropriately (and governed) across an organization.

This webinar will demonstrate the properties of the ideal data and analytics ecosystem for value-based drug development with a real example.

• Demonstrate examples of data integration best practices
• Display state of the art visualization technology
• Demystify predictive analytics and machine learning techniques

Data integration, quality and governance are extremely important fundamental concepts in order for the downstream analytics to occur efficiently. While this topic typically resides within the realm of IT organizations, it is important that development stakeholders understand and contribute to this very important area. Best practices in this realm include, but are not limited to, understanding data sources, formats and the systems in which they reside; common data models, and the role they play in the life sciences industry.

Visualization techniques and products have exploded in recent years, and there are literally dozens of products to choose from. Assessing which one(s) fit your needs is an important topic that is often overlooked. Best practices include, but are not limited to, simple development concepts, native analytics and ability to handle multiple types of data (big, small, complex).

Machine Learning and predictive analytics are often the realm of the Data Scientist and Statistician, however it is important that all types of users understand what the various methods offer. While those with specialized skills are required to administer and develop these methods, there is no reason that anyone cannot at least understand and/or appreciate what predictive analytics can do to help accelerate value-based drug development.

In summary, join us for an exciting session that explores the world of value-based drug development that will provide real examples to many of the questions you may have.

Speaker

Jamie Powers, DrPH, Principal Consultant & Practice Lead, SAS Health and Life Sciences

Jamie Powers is a seasoned analytics professional with a doctoral degree in biostatistics and more than 10 years of experience in the clinical R&D analytics space. He is a member of the SAS Health Analytics Practice, which works with pharma, biotech and CRO customers to discover the power of SAS big data analytics and machine learning. Beginning as a phase 2-4 biostatistician and later taking a leadership role in a predictive analytics group, he developed techniques to drive value in many topics in pharma R&D. Powers also recognized the trend in harnessing big data from various sources to inform clinical R&D decision making. He empowers SAS software users by combining business knowledge with technical expertise.

Message Presenter