YSPH Biostatistics Seminar: “From Randomized Clinical Trials (RCTs) to the Real World: Methods to Enhance RCT Inference"
NOTE: BIS 525 students are required to attend in person. Others are invited to attend in person, but may also attend via Zoom.
SPEAKER: Phyllis Thangaraj, MD, PhD, Clinical Fellow, Department of Cardiology; Post-doctoral Fellow, CarDS Lab; T32 Implementation Science and Research Methods Fellow - Yale University
TITLE: “From Randomized Clinical Trials (RCTs) to the Real World: Methods to Enhance RCT Inference"
ABSTRACT: Randomized clinical trials (RCTs) form the bedrock of medical practice; however, how the information derived from RCTs applies to clinical practice is often uncertain. Our work at the Cardiovascular Data Science (CarDS) Lab has developed models to learn complex multi-dimensional relationships between participants, covariates, intervention arms, and outcomes to characterize RCT generalizability from RCTs to individuals and to populations. This talk will describe novel machine learning methods and their applications to examine treatment effect heterogeneity using multi-dimensional inputs for personalized inference, quantifying the real-world representativeness of RCT participants against corresponding patients in the Electronic Health Record (EHR), and applying generative adversarial networks to examine the implications of an RCT to a new patient population. These studies contribute to a greater understanding of whom the RCT applies to, enhancing inference for real-world patients.
YSPH values inclusion and access for all participants. If you have questions about accessibility or would like to request an accommodation, please contact Charmila Fernandes at Charmila.fernandes@yale.edu. We will try to provide accommodations requested by September 12, 2024.