Back to the program

Invited Paper Session

Advancing Pharmaceutical Research: Estimating Heterogenous Treatment Effects through Virtual Twins

Wed, Aug 6, 2:00 PM - 3:50 PM Room CC-103C Music City Center

Yuxi ZhaoOrganizerJunjing LinChair

Section on Medical Devices and Diagnostics co: ENARco: Section on Statistical Learning and Data Science Applied

5 Presentations

A permutation procedure to detect heterogeneous treatment effects in randomized clinical trials while controlling the type I error rate

2:05 PM - 2:20 PM

Joseph Koopmeiners (University of Minnesota)

Co-authors: Jack Wolf (University of Minnesota School of Public Health), David Vock (University of Minnesota)

permutation test subgroup identification treatment effect heterogeneity type I error virtual twins

Inferring Causal Effects in Subpopulations Using a Matched-Tree Approach

2:20 PM - 2:35 PM

Co-authors: Bo Lu (The Ohio State University)

Potential outcomes Propensity score Matched design Classification and regression tree

Integration of Virtual Twins and Bayesian ML Algorithms in Efficacy Prediction - A Case Study

2:35 PM - 2:50 PM

Yuxi Zhao (Pfizer)

Co-authors: Maria Kudela

virtual twins Conformal prediction Bayesian Causal inference Machine learning

Nearest neighbor (NN) causal Inference for patient-center treatment effect

2:50 PM - 3:05 PM

Bin Huang (Cincinnati Children's Medical Center)

Heterogeneous treatment effect (HTE)Averaged treatment effect (ATE)patient-centered treatment effect (PCTE)k-nearest neighbor (kNN)honest causal forest (HCF)Bayesian adaptive regression tree (BART)

Practical guidance on modeling choices for the Virtual Twins method

3:05 PM - 3:20 PM

Chuyu Deng (AstraZeneca)

Virtual twins Treatment effect heterogeneity

Discussant

Chi Song

↑