Real-world data (RWD) and real-world evidence (RWE) have been used by pharmaceutical companies globally for several decades, but their use has increased significantly in recent years. This has been driven by advances in technology and data analytics that make it easier to acquire and analyze data from real-world sources like EMR, claims and reimbursements, medical devices, SDoH and patient registries. This data, and the evidence it can generate, is used to guide pricing and reimbursement decisions, as well as in the targeting and marketing of treatments.
However, when it comes to use in early phases of the product development lifecycle, its use has been more limited. This is changing though as companies look to the 360-degree view of patients and their journeys that RWE can provide.
Bolstering early-phase activities with RWE is a critical addition to continuous improvement within the pharma industry. With RWE, pharmaceutical companies can improve their ability to identify unmet medical needs and opportunities that can lead to research into new treatments. This in turn can help them focus research and development on areas with higher potential for success.
But perhaps more importantly, it’s become additive to the randomized controlled trial (RCT) process. With some 90% of drugs failing at the clinical trial stage, opportunities to refine the process bring numerous benefits, to pharmas and patients alike.
RWE can also be a major contributor to establishing new-treatment efficacy, and help expedite regulatory approvals. Getting treatments to market sooner means improving patient lives sooner. And a reduction in time-to-market also reduces associated costs and accelerates ROI.
RWE: a clinical trial partner from end to end
RCTs are core to the process of developing new products and having them approved, but they require significant lead times and are expensive to conduct. They also have limitations, sometimes producing results that may not be representative of the patient population. However, when combined with RWE, a more complete view of how drugs and treatments are used and perform in a real-world setting can be achieved, and through efficiency gains, reduce trial duration and cost.
RWE’s use in identifying potential patient populations for clinical trials is an obvious one, but can’t be underestimated. By analyzing real-world data, researchers can identify subgroups of patients who may most likely benefit from a particular treatment or intervention, and use this information to inform the design of clinical trials. It can also help isolate misdiagnosed and under-treated patient cohorts that might expand the trial’s range.
Related to this, it can be used to identify the locations where a particular treatment or intervention is most likely to be used, and then conduct trials at these sites to gain deeper insight into potential performance in the real world.
Another use of RWE in the trial design phase can be in helping researchers identify the most appropriate comparators for a particular treatment or intervention. This information can be used to design clinical trials that are optimized to detect differences between an experimental treatment and real-world comparators, allowing researchers to more accurately assess effectiveness and safety and draw meaningful conclusions about the new treatment’s potential benefits.
A recent article in Therapeutic Innovation and Regulatory Science also noted the potential for RWD-identified comparator cohorts to function in place of placebo control cohorts where the use of placebo might be impractical or unethical. where it is impractical or unethical to run a placebo control arm in an RCT, or to have a control arm at all, RWD external comparator cohorts deliver valuable control populations based on current standards of care.
RWE can also uncover the types of outcomes that are most relevant to patients, based on longitudinal patient journey data for a particular cohort. These outcomes can contribute to the identification and selection of trial endpoints, particularly those that are most sensitive to changes in treatment. The use of sensitive endpoints may increase the likelihood of detecting significant differences between treatments and may be more relevant to patient outcomes
Machine learning detection of inflection points
Machine learning (ML) combined with RWD is a developing area that shows promise for identifying patterns or trends that may indicate an inflection point in the trial. An ML model trained on RWD from a previous trial could identify specific patient characteristics or treatment protocols that are likely to lead to better outcomes. This information can then be used to guide the design and execution of a subsequent trial, with the goal of identifying inflection points as early as possible. RWE-powered ML in this context can also be used to analyze and interpret data from trials in process. This can lead to the detection of inflection points as the trial progresses, allowing for adjustments to be made to the trial on the fly.
The next challenge – turning real-world data into insights, quickly and easily
While the benefits of RWD in pre-clinical trial phases are clear, the application of RWE insights remains problematic for many pharmaceutical businesses.
Real-world data is commercially available, but its diverse range of sources and the scale of the datasets can make analysis expensive and time-consuming. And although numerous RWE tech solutions have emerged over the years, their ability to deliver value has been severely constrained by the need for skilled BI teams that can actually use them.
And there’s the challenge. Pharmaceutical businesses recognize the need for RWE, and have invested heavily into its acquisition and software tools to use it. However, the fact remains that it is too often an untapped asset, procured out of industry wisdom that it will bring value, but locked up from the broad, every-day use within an organization that would actually deliver that value.
Fortunately, a new generation of software is emerging. These RWE platforms are designed for fast and easy refinement of large datasets, leading to on-demand insight into the patient journey, HCP behavior and market dynamics. This is powering patient finding and recruitment, market access strategy, and in-market brand optimization strategy and tactics.
Critically, these platforms augment human expertise on both the software-provider side as well as the pharma-side, to ensure that insights are actionable and that the true value of RWE can be brought to bear across the product life cycle and also – now more than ever – at that crucial, pre-RCT stage.
Talk to Prospection today to find out more about using an RWE platform that turns your RWD investments into ready-to-use insights for enhancing your early-lifecycle-phase projects.