Abstract Number:
1551
Submission Type:
Topic-Contributed Paper Session
Participants:
Xiaofei Wang (1), Herbert Pang (3), Pallavi Mishra-Kalyani (4), Herbert Pang (2), Laine Thomas (5), Yu Shen (6), Xiaofei Wang (1)
Institutions:
(1) Duke University Medical Center, N/A, (2) N/A, N/A, (3) Genentech, N/A, (4) Food and Drug Administration, N/A, (5) Duke University, N/A, (6) UT M.D. Anderson Cancer Center, N/A
Chair:
Co-Organizer:
Discussant:
Session Organizer:
Speaker(s):
Yu Shen
UT M.D. Anderson Cancer Center
Session Description:
Evidence on drug effectiveness and safety often comes from multiple data sources, including RCTs, real-world studies, and population-based databases. However, randomized clinical trials can be underpowered and in some instances their data may not apply to a target patient population. There is an increasing need to conduct statistical analysis or to design clinical trials for better estimation precision, better efficiency, or broader generalizability. As a contrast to naïve approaches, new methodology in this area can leverage the strength of data sources with Bayesian methods, causal inference techniques, data size and quality, treatment selection bias for real-world studies, and sampling bias for randomized clinical trials. This session invites speakers who are at the forefront developing methodology and applying them to extend treatment effect inferences to a new target patient population. Dr. Laine Thomas from Duke University will present on methods that Integrate RCT and external control data using balancing weights. Dr Yu Shen from MD Anderson will talk about statistical inference by integrating external data to improve efficiency of treatment effect estimation in clinical trials. Dr Xiaofei Wang from Duke will talk about threshold detection and patient enrichment and other design issues for multi-stage biomarker-driven clinical trials with information borrowing from historical controls. The invited speakers are the principal investigators of NIH and PCORI grants on statistical methods for integrating RWE with randomized controlled trials. Dr Pallavi Mishra-Kalyani (FDA/CDER) will be a panelist. The session is a collaboration between academia, industry, and the FDA as is co-organized by an academic and industry representative and speakers/discussants are from academia and government. All speakers and panelist have confirmed their availability to present on the conference. The session with health authority policy implications is closely aligned with the theme of JSM 2024 on Statistics and Data Science: Informing Policy and Countering Misinformation.
Sponsors:
Biometrics Section 1
Biopharmaceutical Section 3
International Chinese Statistical Association 2
Theme:
Statistics and Data Science: Informing Policy and Countering Misinformation
Yes
Applied
No
Estimated Audience Size
Medium (80-150)
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand and have communicated to my proposed speakers that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is nonrefundable.
I understand