Zhaohui Su, VP of Biostatistics at Ontada, shared a post on LinkedIn:
“A recent article by Yang and colleagues funded by the Food and Drug Administration (FDA) of the U.S. Department of Health and Human Services (HHS) advocates for the principled integration of randomized controlled trials (RCTs), real-world data (RWD), artificial intelligence/machine learning (AI / ML), and statistical methods to advance evidence generation in clinical research.
It highlights the limitations of relying solely on RCTs or RWD and emphasizes the need for a causal roadmap to clarify inferential goals and ensure transparency.
Key objectives include transporting RCT results to broader populations, embedding AI-assisted analyses, designing hybrid trials, and linking short-term RCTs with long-term RWD. The authors stress that combining statistical rigor with AI/ML innovation will yield robust, transparent, and policy-relevant evidence for regulatory science.
I have summarized the key concepts and findings into a slide deck below. Any comments or feedback are welcome. Thank you.”
Read the full article.