Next Generation RWE: What Factors Are Essential to Fully-Federated and AI-Enabled RWE and Outcomes Research?
Speaker(s)
Faulkner E1, O'Dell D2, Manley A3, Couture N2, Arsenault LF4, Kravchyna M2
1Passage Health Associates, Durham, NC, USA, 2SymetryML, New Jersey, NJ, USA, 3Georgia Institute of Technology, Dublin, Dublin, Ireland, 4SymetryML, Brooklyn, NY, USA
Presentation Documents
OBJECTIVES: While we have made much progress in RWE research approaches and acceptance, fundamental challenges remain that must be addressed to reach a next generation of RWE research. Factors such as numbers of patients of interest in a given dataset, barriers to working across data silos, acceptance of adaptive study designs, data privacy and security, utility of AI, market data restrictions, and methodological challenges limit our access to data and ability to convert it into evidence. This analysis will review these factors systematically and consider where advances are necessary to reach a next generation of RWE.
METHODS: Analysis included literature search of the peer-reviewed and grey literature, in addition to a landscape analysis of next generation RWE solutions that address a set pre-identified challenges. Over 350 peer-reviewed abstracts were analyzed. From this, we have evaluated the degree to which methodological or practical solutions exist and where additional development of RWE approaches are needed.
RESULTS: While next generation RWE solutions were identified that address one or more of the key challenges included in this analysis, few approaches exist that cover many or most challenges. Results suggest that despite drivers like AI and machine learning, evolution of integrated solutions are in the early stages. In the interim, partnerships among solutions providers and HEOR/RWE expert users may improve the ability of the field to fully leverage RWE across the product life cycle.
CONCLUSIONS: As RWE applications and use change rapidly in an increasingly interconnected and AI-enabled world, solutions that address data access, methodological barriers, efficient interoperability, and safe data sharing are critical to evolving the field. Among these, ability to link and share data safely are lynchpin issues that limit ability to address other key challenges and evolve transformative, next generation RWE models.
Code
RWD12
Topic
Health Technology Assessment, Methodological & Statistical Research, Real World Data & Information Systems
Topic Subcategory
Artificial Intelligence, Machine Learning, Predictive Analytics, Data Protection, Integrity, & Quality Assurance, Decision & Deliberative Processes, Distributed Data & Research Networks
Disease
Biologics & Biosimilars, Genetic, Regenerative & Curative Therapies, No Additional Disease & Conditions/Specialized Treatment Areas, Personalized & Precision Medicine, Rare & Orphan Diseases