We all love to talk about the impact big data could have on the biopharmaceutical industry. Having access to so much information has the potential to revolutionize the way we conduct research, build market access strategies, and track real world evidence. But on its own, big data doesn’t add much value. When we connect data with analytic tools and capabilities we produce efficiencies and improvements to patient outcomes that cross the clinical research/healthcare continuum, which is key to gathering the evidence necessary in our value-based healthcare system.
At this year’s West Coast Executive Vision Forum (EVF) we will explore how advances in analytics are already changing the biopharma development and delivery model in three key areas: clinical research, patient outcomes and marketplace value.
Here is a highlight of some of the trends we will cover.
Targeting clinical research
The ability to analyze pooled data sets will help the industry improve study design by creating stronger links between indications and target endpoints, making it easier to identify and validate biomarkers, and to optimize site efficiency and risk management.
- Choosing endpoints: The success or failure of clinical studies is often determined by whether a research team chooses the best primary outcome endpoints to demonstrate efficacy of the therapeutic agent. Clinical validation of surrogate endpoints is required for regulatory acceptance and market access, which typically requires randomized clinical trials (RCT’s) that are complex, time-consuming and expensive. Yet in the end, few surrogate endpoints advance to general practice. The use of real-world evidence, and the ability to analyze large shared data datasets as a supplement to RCTs can enable more rapid validation and acceptance of surrogate endpoints and provide insight into treatment pathways, which can help develop more targeted adherence strategies.
- Selecting biomarkers: Analyzing existing pooled data sets can enable more efficient biomarker identification for clinical research inclusion/exclusion criteria. We have already seen analysis of pooled, metadata sets lead to the identification of multiple drug targets and prognostic biomarkers for a variety of cancers, as well as the discovery and validation of potential drug targets, such as the CD44 cell surface protein in Type 2 diabetes.
- Improving site efficiency: Analytics can be used to drive site-related efficiency measures, including better patient enrollment and fewer protocol amendments. These efficiencies are becoming increasingly important as biopharmaceutical companies pursue therapies to treat new, rare and niche diseases, with smaller patient populations and less clearly understood conditions.
- RBM: Many organizations are already using analytics to execute clinical studies more efficiently via risk-based monitoring (RBM). By pooling data and using rigorous, analytical methodologies to identify site related risks before they create issues for clinical studies, research teams can identify and proactively deal with risks before they impact trail results, and make more efficient use of trial monitors.
Improving patient outcomes
The application of rigorous evidence analysis to real-world treatment patterns, resource utilization and patient outcomes provides actionable insights for healthcare stakeholders that can ultimately improve treatment pathways and patient outcomes, while reaching more physicians and patients with appropriate medicines.
- Monitoring real world outcomes: Electronic medical records have been combined with registries, claims data and other sources of evidence to complement clinical research and drive innovative solutions in patient care. These types of observational studies enhance the breadth and depth of our understanding of the disease condition and ultimately can help us develop treatments and strategies for improving patient outcomes worldwide.
- Custom solutions for non-adherence: Advances in technology and data analytics are enabling new ways to address patient nonadherence. Innovative researchers are applying analytics of large and linked datasets to stratify patients based on risk and consequences of nonadherence, and implementing targeted interventions including apps, and call in centers, to dress the unique obstacles to adherence among different patient populations. Such data-driven targeted approaches can drive improved patient outcomes and lower health system costs through increased medication adherence.
- Understanding the patient journey: By linking real-world data with analytics we can gain insights into patient experience, and their engagement with their own healthcare and healthcare professionals. This approach can help identify physicians who are likely to have patients who may benefit from new medicines and can help manufacturers bring current and relevant educational information to those prescribers efficiently. As drug development becomes more focused on specialty and precision medicine, tailored drug commercialization approaches, such as using longitudinal non-identified prescription information to identify treatment pathways and medication adherence, will become a vital part of their commercialization strategy.
Driving marketplace value
A proliferation of frameworks and assessment approaches now exist around the world to demonstrate therapeutic and economic value in response to increased calls for evidence of the value new medicines bring to patients and health systems. These new approaches increasingly draw upon information and analysis that goes beyond traditional RCT data.
- Proving value in the real world: To make access decisions, payers are requesting information on how drugs will perform in “uncontrolled” patient populations and many are asking for financial guarantees if drugs do not meet thresholds. Insights generated from real-world patient-level data, including electronic medical records, claims data, mortality data, consumer data, registries and other sources, are already being used to provide more accurate information on patients and expected outcomes, support RCT findings over the long term, monitor safety data in a more realistic real-world setting, and to support price re-assessments by demonstrating clinical value. These data sources can also provide ongoing data for payers through “coverage with evidence development” contracts where a rebate or price cut may be required when clinical outcomes are not met, and to help expand indicated patient populations already in early-stage clinical development within EMA’s “adaptive licensing” initiative.
- Expanding therapeutic applications: In disease populations such as in orphan and rare diseases the relative scarcity of precise data for niche diseases and patient populations makes it more challenging to accurately predict valuation and make commercial decisions for drugs developed for these diseases, which can have significant strategic repercussions. To mitigate these challenges, companies are leveraging real-world data to help them better define the population size for known indications, identify undiagnosed and latent patient pools and novel identification of patient segments based on risk predictors, and prioritize indications for asset development. This application of data and analytics is particularly valuable in therapy areas where the disease characteristics, setting of care and/or treatment options present particular challenges. Post-market competitive data may also be used to predict market dynamics. While real world evidence is known to complement data from randomized clinical trials, its real potential is in moving decisions away from broad extrapolations to actual facts about patient journeys and outcomes.
These just a few of the innovation themes we plan to cover at EVF, where thought leaders and industry members will have a chance to network and discuss how these current trends will shape the future of our industry.