Improving Patient Services and Outcomes With Data-Driven Design

According to experts, we currently generate as much data every two days as we did from the beginning of 2000. And that will only grow. By 2020, the amount of data available will have grown from the current 5 zettabytes to 50 zettabytes.¹ How we collect and digest data also spurs a massive shift in our experiences as consumers. Just as Amazon can recommend a product based on your recent purchases, or Netflix might suggest your next favorite series based on your watch list history, data-driven design is transforming the way companies engage with their customers. Now, this same approach can improve patient outcomes in healthcare. These concepts are leading patient support providers to develop more tailored and personalized services.

Program Design

Previously, these decisions hinged on best practices and industry tribal knowledge. Today, program design can take a more calculated approach using data analytics—as part of a multi-pronged approach—to inform patient support services programs. The right patient services partner collaborates with manufacturers to create a more holistic view of each patient journey, using data analytics from multiple sources to identify unspoken patient and provider needs and pinpoint a targeted approach that enhances outcomes and optimizes program spend. If that same partner possesses deep knowledge of provider behaviors, manufacturers receive additional value, translating to a tailored end-to-end solution that improves product access and enhances patient outcomes across all sites of care.

If data-driven design seems promising in theory, it is even more compelling in action. In one example, a program, in existence for more than three years, had an unusual spike in patient drop-off after the completion of the benefit verifications process. Lash Group analyzed the program data, looked through the drop-off reasons and noticed that physician withdrawals spiked significantly during this same period. This observation set in motion a deeper segmentation and targeting analysis, quickly followed by a recommended field strategy and communication plan to reverse this emerging pattern. As a result, the manufacturer achieved a 10 percent reduction in physician withdrawals, many of whom had a high number of patients on that specific treatment. This recommendation, born from a collaborative and comprehensive approach, ultimately helped more patients start and stay on therapy.

Data and Collaborative Analytics

The differentiating factor in this patient service design is collaborative analytics. Collaborative analytics brings together people, processes, data and tools into one cohesive system that is enabled by technology and by an open, adaptive and knowledgeable culture. Beyond program design, collaborative data analytics also increase transparency and wide acceptance of data sharing practices. A decade ago, the pharmaceutical industry designed broad general programs to complement massive, large-volume pharmaceutical product launches. Since that time, healthcare shifted toward specialty and orphan product launches. With more focus on smaller patient populations has come increased scrutiny on how manufacturers engage patients and providers throughout the product lifecycle. Therefore, manufacturers can obtain more nuanced outcomes data that could include information from various touch points. For example, patient interactions with a nurse via a telehealth call can be proactively and collaboratively shared. Collaborative analytics affords manufacturers the ability to leverage the combined knowledge of their analysts and our patient support services analysts to generate deeper insights about smaller, more niche populations.

The rapid growth of healthcare data unleashes the opportunity for deeper and more applicable insight generation. Strong data management practices, therefore, become increasingly important. Consider this example: Lash Group recently executed a project to better understand the impact of patient support service utilization on practice prescriber behavior, patient conversion and patient adherence rates. Ingesting account master data from a manufacturer and matching it against the data available from a physician service organization, ION Solutions, Lash Group analyzed prescribing behavior and payer data, identified provider channel preferences and uncovered a list of providers who were using the services and those whose usage dropped off. These insights became the basis of an updated service program designed, which shifted the mix of services to include the manufacturer sales representatives, ultimately improving the physician experience. After implementation, physician attrition slowed by 10 percent—a significant improvement.

Patient support services data is only one piece of the puzzle. The industry must work together and aggregate data across manufacturers, third-party partners and newly created data sources. Experts recognize that it takes collaboration to optimize design, performance, and patient and provider experiences. As the depth of collaborative analytics grow, more strategic and targeted recommendations on how to optimize patient services will come to fruition.

^{1. Bernard Marr & Co. What is Big Data? A super simple explanation for everyone. Accessed 15 September 2017. Available online at https://www.bernardmarr.com/default.asp?contentID=766.}