What will make real-world evidence regulatory grade in 2026 and beyond?

Key Takeaways: 

• Forward-thinking life sciences organizations are shifting from short-term planning to long-term, lifecycle-focused approaches that unlock the power of real-world data (RWD) and real-world evidence (RWE).
• When combined with robust, de-identified patient datasets, artificial intelligence (AI) technologies deliver speed to value and help differentiate organizations in the market. 
• Pfizer partnered with Premier Applied Sciences to raise the bar for RWE as an engine for quality, credibility and impact in regulatory and scientific decision-making.

The path to regulatory approval is evolving, shaped by new technologies, richer data sources and rising expectations about what counts as credible, actionable evidence. Today, real-world evidence (RWE) is helping establish faster, more flexible evidence development — generating earlier, richer insights, supporting smarter trial design and paving more efficient paths to regulatory approval and commercialization.

When multinational pharmaceutical and biotechnology corporation Pfizer partnered with Premier Applied Sciences, the two companies shared a noble vision: to raise the bar for how RWE can be leveraged in regulatory and scientific decision-making, fostering greater transparency and trust in service of better patient outcomes.

“We’ve seen a change over the last several years when we talk about what makes data regulatory- grade,” said Jennifer Webster, Pfizer’s Vice President, RWE Platforms and Partnerships. “In the past, determining whether something was regulatory-grade focused on things like missing values in a column or whether individual data values had been validated — and that's still important.

“But today, when we talk about regulatory-grade RWE, we're now also saying, ‘Do you understand the provenance of the data? Have you validated your endpoints, your exposures and your covariates?

“Increasingly, regulators are asking for proof that (the insights) we're pulling out of real-world data (RWD) have meaningful clinical correlation to what's happening to those patients in the real world.”

This deepening understanding of and appreciation for the clinical context of RWD enables a more strategic approach to evidence generation — one that looks beyond immediate needs to the full lifecycle of a product, from early-stage development through regulatory approval and beyond. 

Taking the Long View of Evidence Generation

With 37 manufacturing sites worldwide, Pfizer approaches evidence generation with a long-term, integrated mindset. Rather than treating studies as isolated moments, the company designs strategies that anticipate the evolving needs of regulators, payers and patients throughout an asset’s lifecycle. 

“Pfizer, like many peer companies, is doing really formal integrated evidence planning,” said Webster.

“That integrated evidence planning means we’re taking a holistic view of all the evidence coming out of our clinical programs — and then identifying any evidence gaps we still need to close using real-world data or other evidence-generation strategies. 

“We’re trying to understand what that holistic evidence package looks like across all our stakeholders and how we can deliver it in a timely way. 

“Our goal is to ensure we always have the right evidence available for our payers, healthcare professionals, patients, regulators and other stakeholders who rely on that evidence to make timely, informed decisions.”

Such integrated planning ensures that evidence generation is not reactive but strategic, anticipating needs and closing gaps well before they arise. This mindset empowers teams to align clinical development, RWD strategies and stakeholder needs — creating a continuous, coordinated flow of evidence that supports an asset’s success from early development onward.

“Instead of planning year by year, we're looking ahead five, 10 or even 15 years depending on the asset.” Webster said. “We’re starting to think about the different types of evidence we'll need as that asset matures.”

Integrated RWD Across Study Types

Clinical trials are another area where RWD is becoming more integral to how evidence is generated, interpreted and applied: RWD informs nearly every stage of evidence generation, from site selection in randomized, controlled trials to the design of pragmatic, low-intervention studies where most data are gathered in real-world settings. 

“RWD now informs nearly every type of evidence generation we do, including truly randomized control trials,” said Webster. “We still use RWD to inform site selection. We are also conducting more pragmatic or low-interventional trials, where most of the data is coming from real-world settings, but we may collect a few additional labs or instrument measures. On the observational side, we often combine retrospective data with primary data collection, sometimes within the same study. This helps ensure each protocol is carefully calibrated to deliver the specific evidence we’re targeting.” 

In turn, these varied applications of RWD contribute to the broader generation of RWE that informs clinical, regulatory and commercial decisions. As this evidence base becomes foundational across study designs, the ability to handle diverse, complex and unstructured data is becoming more important than ever. From clinician notes to imaging, harnessing the full potential of RWE requires not only access but also advanced tools and partnerships to extract meaningful insights at scale. Increasingly, AI-enabled technology is transforming how RWD is used and interpreted across study designs. 

Unlocking Value from Unstructured Data with AI

To get the most benefit out of RWD and RWE, finding the right partner is critical. Pfizer works with Premier Applied Sciences to advance the use of RWE in regulatory submissions and global evidence generation.

Premier provides validated, regulatory-grade RWD. Pfizer integrates this data into its evidence planning and research strategies, validating endpoints, exposures and outcomes that reflect real clinical practice. This, in turn, strengthens the quality and credibility of RWE used for scientific decision-making and regulatory submissions, helping accelerate the translation of data into meaningful healthcare impact.

Within the Premier Healthcare Database (PHD) — one of the most comprehensive repositories of de-identified electronic healthcare data — robust patient datasets are often combined with AI-powered machine learning (ML) to process data and recognize patterns. Natural language processing (NLP) further enhances this capability, quickly finding needle-in-a-haystack insights within massive amounts of healthcare data. The technology can read and interpret more than 2 million records per hour, delivering timely, deep insights for clinical decision-making. Meanwhile, it helps feed a growing demand for high-quality RWD that reflects the complexities of clinical care and the opportunity to make that data meaningful on a global scale. 

As regulatory bodies continue to look to RWE for insights that support approvals, safety decisions and post-market surveillance, the collaborative effort between Pfizer and Premier stands as a model for what’s possible when data breadth and quality and research prowess come together. It’s not just about generating evidence — it’s about transforming that evidence into actions that improve healthcare outcomes.

For more:

Discover how Premier’s RWE expertise can help your organization turn data into actionable insights, support smarter regulatory submissions and drive faster approvals and stronger outcomes. See how our RWE solutions deliver real results for life science organizations.

Interested in ongoing updates from Premier Applied Sciences? Subscribe to Premier Perspectives to get timely updates in your inbox.