Generative AI: Driving the Next Era of Evidence-Based Medicine

Moderator

Eric Q Wu, PhD, Analysis Group, Boston, MA, United States

Speakers

Jimmy Royer, BA, MA, PhD, Analysis Group, Montreal, QC, Canada; Rajeev Ayyagari, Analysis Group, Boston, MA, United States; Frank Hu, MD, PhD, Cambridge, MA, United States

Generative AI (GenAI) is transforming health economics and outcomes research (HEOR) and real-world evidence (RWE) by enabling new ways to analyze large datasets, model complex phenomena, and support evidence-based decision making.

Powered by large language models (LLMs), GenAI enables richer analysis of diseases and treatment outcomes and more efficient insight extraction from diverse data sources such as electronic health records, claims data, and scientific literature. These capabilities are unlocking new opportunities to advance health care innovation and improve patient outcomes.

This symposium will explore the frontiers of GenAI, highlight key developments and challenges, and showcase its applications in HEOR and RWE. Case studies in disease areas such as oncology, obesity, and cardiometabolic diseases will illustrate how GenAI can advance research with real-world data (RWD). Presenters will demonstrate how data from electronic medical records, disease registries, and population-based cohorts can be curated, linked, and enriched to generate insights that are both context-specific and globally relevant.  The session will also introduce a new RWE research initiative jointly launched by Harvard School of Public Health and Analysis Group to advance precision health and to apply AI to deepen our understanding of disease and treatment outcomes.

Presenters will discuss how GenAI can streamline the automated screening of published research by translating and summarizing scientific literature across multiple languages. They will demonstrate how these advances expand access to comprehensive evidence, enabling more accurate and timely decision making.  

Finally, the symposium will present an example of combining GenAI with digital twin methodologies to model the long-term progression of obesity and chronic cardiometabolic conditions. Together, these innovations promise to simplify complex analyses, enhance research precision, and deepen understanding of disease pathways. Ultimately, GenAI offers powerful tools to strengthen evidence-based decision making and shape more effective health care solutions and policies.

Sponsored by Corporate Partner, Analysis Group.

Code

027

Topic

Methodological & Statistical Research, Real World Data & Information Systems, Study Approaches

Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on ispor.org. Update my browser now

×