Session (CTI)

Generative AI (GenAI) is increasingly being explored as a tool for the analysis of large-scale, multi-modal, and multi-source data in order to model complex diseases, evaluate treatments, and support evidence-based decision making. Powered by large language models (LLMs), GenAI may support the synthesis and interpretation of diverse data streams – including electronic health records, claims data, disease registries, population-based cohorts, and scientific literature – to examine patterns in disease progression and treatment outcomes.
This symposium will explore the frontiers of GenAI in evidence-based medicine, highlighting recent advances, methodological challenges, and practical applications. Presenters will demonstrate how heterogeneous data sources can be enriched and integrated to generate context-specific yet globally relevant insights. The session will also introduce an emerging research initiative focused on advancing precision health through the application of AI to better understand disease pathways, treatment effectiveness, and personalized health.
In addition, the symposium will showcase the application of GenAI with digital twin methodologies to simulate the long-term progression of obesity and chronic cardiometabolic diseases, enabling exploration of long-term treatment impacts. Collectively, these innovations highlight emerging approaches for analyzing complex relationships within healthcare data, supporting integrated, multi-disease analyses while strengthening methodological rigor in AI-enabled evidence generation. By strengthening the generation and interpretation of real-world evidence, GenAI, together with diverse data ecosystems and collaborative research efforts, may contribute to evolving approaches in evidence-based decision making and health policy analysis.
Sponsored by Corporate Partner, Analysis Group