The Growing Power of AI and Real-World Data in Commercialization

Elliot Zimmerman, chief commercial officer, Verana Health

Regulatory approval is hardly the end of the journey from laboratory to patient. Often heralded as a triumph, this milestone in fact marks the beginning of a new phase: commercialization.

Unfortunately, commercialization too often gets underestimated. Despite encompassing manufacturing, supply chain, market access, reimbursement, marketing, sales, and on-going surveillance and monitoring, commercialization almost seems to be treated as an afterthought.

When organizations rely on outdated systems, fragmented data, or static planning cycles, a disconnect arises between market opportunities and execution. Companies become slow to identify the right prescribers, engage patients, and respond to market shifts.

Increasingly, however, the power of artificial intelligence (AI) and real-world data (RWD) is opening a window to a more holistic view of the patient journey—and the insights to fine-tune commercialization strategies.

AI-curated RWD has already demonstrated value in improving clinical research, including optimizing protocols, site selection, and enrollment. Forecasts expect sustained growth in the real-world evidence (RWE) market, and recommendations encourage integration of RWE in the early development of clinical studies.

Now, RWD is also becoming a critical tool for commercialization, helping companies better understand disease progression, patients’ responses to drugs, and strategies for long-term treatment.

RWD as a Window Into the Market

RWD encompasses a range of health care information from sources including medical claims, electronic health records (EHRs), and wearable devices. Much of this data—such as clinician notes and imaging reports—is unstructured, making it difficult to analyze with typical database queries.

Yet the observations, assessments, and treatment plans tracked in clinical notes contain significant detail of a patient’s condition and experience. Until recently, the challenges of digesting massive volumes of unstructured data limited the practical utility of EHR data in clinical research and drug development.

With advances in AI, particularly machine learning (ML) and natural language processing (NLP) models, it’s now possible to curate and harmonize unstructured RWD at scale and with unprecedented speed, unlocking significant potential.

This allows for continuous monitoring of patient treatment patterns and prescriber behaviors over time. With the right tools, pharmaceutical companies can now assess the competitive landscape and make more informed business decisions based on current market information.

This awareness includes understanding how a therapy is performing relative to alternative treatments, tracking new product launches, market shifts, and therapy preferences among prescribers. This knowledge, based on real-world usage, can help pharmaceutical companies identify opportunities to differentiate their products.

Examining Patterns of Treatment

Traditional market surveys typically have inherent flaws and come up short when it comes to gauging market dynamics.

By actively monitoring RWD—tracking brand initiations, switches, and discontinuations, as well as analyzing treatment frequency—pharmaceutical companies gain valuable insights that can influence product positioning.

With RWD, companies get a view into patient journeys across various related therapies. This information sheds light on telling questions. For instance: Are patients starting treatment quickly enough? Is the therapy prescribed appropriate for the disease stage and patient profile? What is motivating off-label prescriptions, and do physicians need education on more effective on-label products?

When integrated with payer coverage data, RWD fills in crucial pieces of the patient journey. It can show if a patient is unable to access a drug and why. With this information, pharmaceutical companies can fine-tune their commercial strategies, improve patient access, and ultimately boost market share.

Understanding Brand Switching

The reasons patients transition from one medication or therapy to another remains one of the most underexplored areas in pharmaceutical strategy. Yet understanding why patients and prescribers switch is essential for developing effective strategies, improving product positioning, and increasing market share.

A brand switch can be driven by effectiveness, cost, side effects, treatment burden, or prescriber preference. But prescribers' motivation for switching patients from one treatment to another can’t always be inferred from structured data.

The clues often reside in EHR clinical notes—unstructured data. To gain insights from this data, manual chart abstraction simply isn’t practical at scale. Employed correctly, large language models (LLMs) can effectively extract the reasons for treatment switching.

With more generics and biosimilars in the marketplace, patients switching driven by access to lower out-of-pocket costs may result in better adherence to treatment. RWD can reveal the number of patients switching from originally prescribed treatments to a generic or biosimilar and the cost differentials. Surfacing these insights at scale supports more informed product strategy, market access, and medical engagement decisions.

Prescriber Mapping

An informed understanding of prescriber behavior greatly improves the effectiveness of launch messaging and prescriber targeting efforts.

RWD can help pharmaceutical companies identify the key influencers in a market and target the precise prescribers to optimize product adoption and engagement across geographies and settings.

Additionally, RWD can help companies better understand the prescriber networks that influence treatment decisions. By studying trends and practice patterns, companies can tailor communications to reach prescribers who are influential in community networks, group practices, or academic medical centers. Leveraging peer influence, pharmaceutical companies can work with opinion leaders to strengthen awareness and adoption of therapies across networks of prescribers.

RWD can identify prescribers with exhibited loyalty to specific therapies, enabling pharmaceutical companies to target engagement in order to strengthen brand affinity. This can also identify potential competitive threats by tracking prescribers volume of procedures or prescriptions across brands and examining the causes for changes in prescribing behavior.

A Realm of Benefits

The strategic use of RWD offers pharmaceutical companies an array of benefits and market insight for improving commercialization.

The comprehensive nature of RWD affords a holistic view of patients, clinicians, and therapies. With product launches hinging on timing, targeting, and traction, the AI-curation of RWD enables teams to identify the relevant patient subgroups, geographic markets, and prescribing behaviors—well before launch.

A critical advantage of RWD is the actionable nature of its insights: effectively translating complex data into information that can guide strategic decisions. With it, decision makers can understand market trends, identify patient and customer segments, and benchmark against competitors to enhance strategic planning.

By transforming RWD into RWE, companies can develop enhanced market understanding, identify challenges, and uncover key opportunities. By illuminating patient journeys and treatment adherence patterns, companies can align products and strategies more effectively with real-world demands.

By incorporating EHR outcomes data into analytics, companies can compare their product performance against industry benchmarks and competitors. This analysis helps in the refinement of commercial strategies to improve market positioning beyond what claims data offer.

Advancing the Science of Commercialization

The potential of RWD and AI in commercialization is rapidly evolving into execution. With research citing use of RWE in commercialization as a top return-on-investment strategy amongst pharmaceutical companies, organizations that act decisively can gain an edge, ensuring that their strategies remain timely, informed, and relevant.

Failing to leverage RWD puts any commercialization strategy on shaky ground. By harnessing the power of AI and RWD, pharmaceutical companies achieve a holistic view of the patient journey beyond the lab, which is critical to optimizing market potential and, most importantly, improving patient access to vital therapies.

About the Author

Elliot Zimmerman is the Chief Commercial Officer at Verana Health where he oversees Business Development and Sales, Customer Management, Delivery and Customer Support. Elliot brings 25+ years of leadership experience in enterprise software and services, overseeing sales, account management, delivery, support, compliance, and data security teams. Before joining Verana Health, he was CEO of Real Life Sciences for five years, where he led the business to a 15× increase in ARR and achieved positive EBITDA, leading to its acquisition by MediSpend, Inc. in January 2025. Previously, Elliot served as COO of goBalto until its acquisition by Oracle in 2018, and held leadership roles at Model N and Manugistics.