Advancing Drug Development and Regulatory Compliance with AI-Enhanced Real-World Evidence

In recent years, regulatory bodies, such as the Food and Drug Administration (FDA) and the European Medicines Agency (EMA) have increasingly emphasized the use of real-world data (RWD) in clinical research and regulatory decisions, recognizing its potential to enhance drug development and improve patient outcomes. This shift includes a focus on sourcing RWD that adheres to strict regulatory standards for effective use in drug approvals and postmarket surveillance. 

Unlike traditional data from controlled clinical trials, RWD comes from varied sources such as electronic health records, claims databases, and medical imaging, reflecting real-world patient experiences and outcomes. This type of data offers a broader and more comprehensive view of how therapies perform outside clinical trials, allowing researchers and regulators to access insights across more diverse patient populations. However, RWD is often complex and unstructured. Approximately 80% of clinical data is unstructured and untapped. Artificial intelligence (AI) plays a pivotal role in enhancing the quality and accelerating the usability of RWD to prepare it to for regulatory-grade real-world evidence (RWE).

Insights from 2024 FDA and EMA Regulatory Guidance

Recent regulatory guidance, particularly the FDA’s July 2024 guidelines, highlights RWD’s potential to accelerate drug approvals and enhance postmarket surveillance, especially for diseases hard to study in traditional trials. The FDA guidance emphasizes critical factors, such as selecting representative data sources, ensuring data quality, designing studies to mitigate biases, and maintaining transparency for replicability. 

Similarly, the EMA’s 2024 report on RWE framework focuses on harmonizing data standards, outlining regulatory science strategies, and promoting collaborations to integrate RWD into regulatory decisions effectively. These guidelines aim to bolster the reliability and relevance of RWD in regulatory submissions, thereby enhancing the evidence base for treatment safety and efficacy.

Insights from the IRIS^® Registry

The field of ophthalmology is one such space where the integration of RWD and AI promises to generate high-quality evidence that meets the stringent requirements of both U.S. and European regulators.

As one of the largest specialty society clinical data registries in all of medicine, the American Academy of Ophthalmology IRIS^® Registry (Intelligent Research in Sight) provides an invaluable source of RWD for ophthalmology research in the U.S. With data on 80 million de-identified patients from 15,000 contributing clinicians over 11 years, it is the most comprehensive data source for ophthalmology, with regard to the completeness, accuracy, and plausibility of the data, as described in the FDA guidance on RWD.

The FARETINA-AMD study leveraged the IRIS Registry to identify 12,000 eyes which reflected diverse patient outcomes of faricimab for treating neovascular age-related macular degeneration (nAMD). The study focused on real-world treatment patterns and safety outcomes, comparing them to results from the phase 3 clinical trial. Notably, the RWD revealed fewer safety incidents than those observed in the controlled clinical trial setting, demonstrating the therapy’s strong safety profile in a broader, more diverse patient population. This is a crucial finding, as it highlights how RWD can complement clinical trials by reflecting outcomes in everyday clinical practice, which often includes more complex and comorbid patients than those enrolled in trials.

Moreover, the study found that a significant proportion of patients, both treatment-naive and those previously treated with other anti-VEGF agents, were able to safely extend the intervals between faricimab injections while still reporting positive results. This points to a key advantage for patient compliance and overall treatment management. These insights into both safety and dosing interval flexibility demonstrate how RWD from representative, quality data sources, such as the IRIS Registry, can provide a deeper understanding of a therapy’s performance in real-world settings. Such knowledge is essential for clinical decision-making and regulatory evaluation to ensure alignment with FDA standards that call for robust, regulatory-grade RWD.

The foundation of the regulatory-grade RWD in this study lies in the quality of the underlying data, as defined by the FDA and EMA. Data must be collected and curated to meet the highest standards of accuracy, completeness, and reliability to ensure AI is being applied in a way that enhances, rather than compromises, the quality and reliability of the RWE generated.

Harnessing AI and RWE for the Future of Ophthalmology

The integration of AI and regulatory-grade RWE is transforming the landscape of clinical research. In ophthalmology, where traditional clinical trials can face challenges, such as limited patient populations, or ethical concerns around placebo use, AI-powered RWE provides a practical and scalable solution. It enables researchers to make use of rich data sources, such as the IRIS Registry, to support regulatory submissions, improve postmarket surveillance, and generate insights that are reflective of real-world patient outcomes.

About Sujay Jadhav

Sujay Jadhav is the Chief Executive Officer at Verana Health where he is helping to accelerate the company’s growth and sustainability by advancing clinical trial capabilities, data-as-a-service offerings, medical society partnerships, and data enrichment. Sujay joins Verana Health with more than 20 years of experience as a seasoned executive, entrepreneur, and global business leader. Most recently, Sujay was the Global Vice President, Health Sciences Business Unit at Oracle, where he ran the organization’s entire product and engineering teams. Before Oracle, Sujay was the CEO of cloud-based clinical research platform goBalto, where he oversaw the acquisition of the company by Oracle. Sujay is also a former executive for the life sciences technology company Model N, where he helped to oversee its transition to a public company.  Sujay holds an MBA from Harvard University and a bachelor’s degree in electronic engineering from the University of South Australia