In anticipation of her upcoming conference presentation at Predictive Analytics World for Healthcare New York, October 29 – Nov 2, 2017, we asked Anna Kondic, Executive Director, Predictive Economic Modeling at Merck, a few questions about incorporating predictive analytics into healthcare. Catch a glimpse of her presentation, Predicting Survival in Lung Cancer Based on Early Clinical Readouts using Modeling of Literature Data, and see what’s in store at the PAW Healthcare conference in New York City.
Q: In your work with predictive analytics, what area of healthcare are you focused on?
A: I have recently switched from modeling support in clinical development to economic evaluation of medicinal products and technologies. While the context and the audience are different in the two fields, there is a surprisingly large overlap in the analytical approaches.
Q: What outcomes do your models predict?
A: In biopharma, modeling has been used for a variety of R&D applications and products. For example, predictive modeling can be used to extrapolate across patient populations, early and late clinical endpoints, and to evaluate hypothetical scenarios before an investment is made.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions or impacts operations? Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: Merck has applied predictive analytics in the regulatory filing of our immuno-oncology medicine. Modeling was used to demonstrate the equivalence of two doses that were tested in the various clinical trials for melanoma and non-small cell lung cancer even though the patient populations tested were different in their characteristics and size. Applying analytical approaches like this can help accelerate clinical development and approval — processes that usually take a long time — and get needed medicines to patients sooner.
Q: What surprising discovery have you unearthed in your data?
A: It is not so much surprise, but a joy in a couple of occasions, when I see how my work as a data scientist matters in helping patients in ways that had not been seen before. For me, this is a very personal journey.
Q: What areas of healthcare do you think have seen the greatest advances or ROI from the use of predictive analytics?
A: In the 15 years I have been in the industry, I have seen tremendous progress in terms of data availability and quality, both in the public and private sectors. Such improvement has been possible due to development in technologies (e.g. imaging and genome sequencing), as well as further advancement in computer performance. I think that we are living in the golden times, where the analytics will catch up and we will see some meaningful outcomes and progress in understanding human disease and personalized medicine.
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: I will discuss an example where we could predict a clinical outcome a few months before the actual data became available. This is a tool that can inform internal decision making in time of constrained resources.
Don’t miss Anna’s presentation, Predicting Survival in Lung Cancer Based on Early Clinical Readouts using Modeling of Literature Data, at PAW Healthcare on Tuesday, October 31, 2017 from 3:30 to 4:15 pm. Click here to register for attendance.
By: Jeff Deal, Conference Chair, Predictive Analytics World Healthcare