Proactively Identifying & Addressing Affordability Issues with Predictive Analytics

In this Pharmaceutical Executive video interview, Kimberley Chiang, vice president of biopharma commercial solutions at CoverMyMeds, discusses "The 2025 Medication Access Report." She highlights gaps in data-sharing and cross-functional collaboration as major bottlenecks that cause delays, rework, and increased patient burden. Chiang shares that only 3% of patients utilize support programs due to a lack of awareness. A large majority of the report's respondents plan to expand funding for patient support programs within the next 5 years due to large number of new therapies expected to come to market.

Pharmaceutical Executive: How can the industry leverage data and technology to proactively identify and address affordability issues before they become a barrier to patient access? What role does predictive analytics play in this?
Kimberley Chiang: The ability to be proactive in identifying and addressing those gaps requires a centralized data system and a greater ecosystem. The ability to leverage data requires that data to be comprehensive. Predictive analytics will run on strong data models, and in order to have those, you need a seamless experience.

How do we capture data along the patient journey, and how do we ensure that predictive analytics will help us analyze that data? It all starts with the ability to streamline the data. If we don’t begin to bring data sources together in real and important ways, we will not be able to properly allocate our resources and spending in pharma. There will be some forecasting and assumptions, but with some real-world data (RWD) integrated.

Think about the addition of an integrated data model with RWD and what that could do for better predictive analytics. Our assumptions would be lowered, and our predictions would be better. We would have optimized predictability for where the funding needs to be directed.

The second piece of that is you have better clinical outcomes if you can identify in advance. You will not have patients walking away from their prescriptions, which continues to be a challenge. We are also seeing significant increases in claims denials. About 73% of claims are denied. What do we do when claims come back denied?

With predictive analytics, there are affordability and co-pay types of expansion. There’s also focus and energy around overturning claim denials. How do we ensure that the claim was denied for righteous reasons? The ability to have all of the data integrated and run it through predictive analytics alongside RWD would help us improve clinical outcomes. Those patients will not be denied medication that they need and rightfully deserve.

Doing all of this more efficiently will remove costs from the ecosystem. There is significant fragmentation in all of the processes. To bring all of that data together to understand the market access for a single brand launch, bio-pharmas must piece together all of that information. Bringing data together and using predictive analytics with strong data models will help these companies do so more efficiently. It will take costs out of the system and speed patients onto the right medications. Healthcare providers will also spend less time waiting for the patient to get approved.