Saturday, October 31, 2026

10:30 - 12:00

Lecture Theatre 3

---

Details

Cross-country real-world evidence (RWE) is increasingly needed, but privacy and data governance constraints often limit centralized data sharing. Federated, privacy-preserving analytics can support collaborative evidence generation across distributed healthcare data systems, while advances in AI and causal machine learning may improve scalability and heterogeneity assessment. A key question is whether these approaches can generate transparent, reproducible, and decision-grade evidence for regulatory and HTA use. This symposium will examine how privacy-preserving, federated analytics may bridge methodological innovation and decision-grade evidence for regulatory and HTA decision-making. It will review distributed data networks, federated learning, causal AI, and federated target trial emulation, with attention to transparency, validation, and evidence standards. The session will also address implementation challenges, including privacy-preserving workflows, cross-border data constraints, and the diversity of healthcare and data governance environments across Asia. Presentations will reflect complementary perspectives from academia, regulatory science, industry, and applied evidence generation. Discussion will focus on methodological standards, study design, AI validation, and documentation to support trustworthy federated RWE for regulatory and HTA use, and broader adoption of scalable, privacy-preserving, AI-enabled evidence approaches. • Assess how privacy-preserving, federated, and AI-enabled approaches may support RWE across distributed data networks. • Identify considerations for translating methodological innovation into transparent, reproducible, decision-grade evidence for regulatory and HTA use. • Recognize methodological and operational challenges affecting the credibility and acceptability of federated RWE. • Apply lessons from emerging examples to inform decision-grade evidence generation. Relevant to pharmacoepidemiologists, RWE scientists, biostatisticians, regulators, HTA stakeholders, and researchers interested in privacy-preserving evidence generation.

---

Speaker