Fresh from the dynamic and idea-rich environment of ISPOR 2025, the premier global conference on health economics and outcomes research (HEOR), one message emerged loud and clear: innovation is rapidly reshaping the HEOR landscape, yet foundational challenges remain that require renewed attention and action.
Amid the buzz around harnessing real-world data (RWD), influencing regulatory decisions, and leveraging new analytical tools, three strategic priorities rose to the forefront: aligning data with purpose, closing knowledge gaps among stakeholders, and applying advanced analytics with care and precision.
The evolution of HEOR is accelerating, and with it, the expectations placed on researchers, pharma leaders, regulators, and payers. Here is how the field is advancing and where our collective focus should be as we enter this next chapter.
Starting with the Right Question Transforms RWD into Real Impact
RWD continues to be central to HEOR. Yet, despite decades of use, one of the most basic challenges remains: ensuring data, methods, and intended use are truly aligned. Too often, researchers are guided by data availability rather than data fitness for purpose.
The most effective research does not begin with a dataset; it begins with a question. From there, a structured process is required to identify the appropriate data source and analytic approach. That discipline is what gives findings their integrity and relevance.
Takeaway: All data and methods come with limitations. Researchers must match the question to the data, to the method, to the intended use. The studies that succeed in delivering credible insights are those that design around these constraints with intention and rigor. Sensitivity analyses and transparent frameworks are no longer optional; they are essential.
Bridging the Understanding Gap Builds Trust in Real-World Evidence
As RWD shifts from exploratory insights to decision-grade evidence, a growing issue is surfacing: many key HEOR stakeholders still lack a clear understanding of what RWD can, and cannot, deliver.
Terms like “missingness” and “quality” are often misunderstood. All data sources have “missing” data, but that does not mean the data cannot be used. It is critical to understand why some data elements may not be captured as someone may expect, and also to challenge those expectations. Further, known unknowns can be accounted for in methods and analytics, which is why data expertise is needed when ascertaining fitness for purpose within the context of a specific question.
Misinterpretations of data concepts like “missingness” and “quality” can erode trust and hinder adoption, especially when stakeholders expect real-world evidence (RWE) to behave like data from randomized controlled trials.
Key Insight: While neither the data nor the methods are perfect, the results can still be reliable—what matters most is understanding the complete context of the question. Imperfect data does not mean failure; it reflects reality. Building trust in RWD takes concerted effort to educate stakeholders about how to interpret RWE within the right context.
Advanced Analytics Demand Human Intelligence to Unlock Their Potential
Artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) are becoming integral parts of the HEOR toolkit. But their power can be undermined when used without a deep understanding of the data feeding them.
Running complex models is no longer the hard part. The real challenge lies in understanding the data that is being fed into the model and then interpreting the model’s output correctly. Even advanced analytics have produced results that were clearly wrong, simply because key data context was misunderstood.
For example, NLP models may struggle to determine something as seemingly straightforward as smoking status or COVID-19 positivity when clinical notes contain conflicting or repetitive information. Temporality, negation, and nuance make data extraction a relatively difficult task to get correct with a high level of precision.
Bottom Line: Advanced technologies must be paired with deep domain expertise. Health economists, epidemiologists, and data scientists must collaborate closely to ensure models are valid, interpretable, and useful.
TriNetX Sets a New Standard for Research You Can Trust
At TriNetX, we address these HEOR challenges through a systematic and thoughtful methodology. Every engagement begins with a rigorous, deep fitness-for-purpose assessment, whether we are conducting a study or licensing a dataset. This ensures that the data can truly support the research question and intended use.
We also leverage ML extensively to identify patients who are difficult to find, such as those with rare diseases. These are often cases where there are no established cohort or outcome definitions, making traditional approaches less effective. Our models help surface patients who may meet complex or undefined clinical criteria, enabling more precise and targeted research in areas that lack validated frameworks.
Our impact is demonstrated not just in outputs, but in outcomes: TriNetX RWD has supported more than 1,000 peer-reviewed publications across therapeutic areas including oncology, cardiology, neurology, and ophthalmology. These publications reflect more than academic progress; they are shaping clinical practice, regulatory decisions, and health policy globally.
Global Depth and Data Diversity Are Driving the Next Wave of HEOR Progress
The demand for deeper data—genomics, imaging, microbiology, antimicrobial resistance, and more—is intensifying. And it is not just a U.S. phenomenon. Globally, researchers and sponsors want more detail, more precision, and more breadth across diverse healthcare ecosystems.
But accessing and using this data is challenging. Much of it lives in non-standardized formats across disparate systems. Success will depend on strong partnerships with healthcare organizations and the ability to return to the source for validation.
At TriNetX, our partnerships with global healthcare organizations enable us to go deeper, with integrity. Whether it is liberating device identification data, oncology detail, or genomic sequences, we prioritize quality, traceability, and scientific defensibility.
The Future of HEOR Belongs to Those Who Lead with Evidence and Discipline
In a marketplace saturated with bold claims and buzzwords, credibility will belong to those who act with discipline. Whether you are leading a market access strategy, evaluating treatment value, or developing policy, the challenge is not having more data, it is having the right data, used in the right way, with the right expectations so that the findings will withstand rigorous review and be actionable.
The HEOR community must continue to push boundaries but do so thoughtfully. The next chapter is not just about innovation. It is about trust, robust evidence generation, and responsible evolution.
About Jeffrey Brown, PhD
With more than 25 years of experience in research and consulting, Jeff is an internationally recognized expert in the use of RWD to support the evidentiary needs of regulatory agencies and medical product sponsors and an expert in the assessment of data quality of RWD resources.
