June 21, 2021 Webinar
Modeling complex survival outcomes with large-scale genetic covariates: methods and applications
Ying Ding, PhD
Abstract:
Complex survival outcomes such as multivariate or interval-censored endpoints become more commonly used in randomized clinical trials (RCTs). Moreover, many modern RCTs also collect large-scale genetic/genomic data for the potential of individualized risk prediction and personalized medicine development. The complex survival outcome together with large-scale genetic data pose great analytical challenges for such studies. Motivated by studying the progression and genetic causes of age-related macular degeneration (AMD), a devastating bilateral eye disease, where bivariate interval-censored outcomes and large-scale GWAS data are collected, we develop several novel statistical methods to enrich the discovery of risk factors, to improve the prediction of disease progression and to confidently identify and infer subgroups with beneficial treatment effect. In this talk, I will introduce (1) flexible copula-based modeling and test for bivariate interval-censored data, (2) survival-model-based deep neural network for individualized prediction of disease progression, and (3) Multiple-testing-based confident subgroup identification and inference for survival outcomes. Both statistical and computational aspects of the methods, as well as their in-depth applications will be discussed.
Short Bio:
Dr. Ding received her BS in Mathematics from Nanjing University, China, and her PhD in Biostatistics from the University of Michigan in 2010. She then joined Eli Lilly and Company as a Research Scientist and then a Senior Research Scientist, doing clinical trials and personalized medicine research in type 2 diabetes. Motivated by her passion in teaching and research, she pursed an academic career by joining University of Pittsburgh in 2013. She is currently a tenured Associate Professor at the Department of Biostatistics, University of Pittsburgh. Dr. Ding's main research areas include survival analysis, large-scale genomics and proteomics analysis, multiple testing, and precision medicine. So far, she has published about 60 peer-reviewed papers, four book chapters and one book (as a co-editor). She is Associate Editor for Statistics in Medicine and Journal of Statistical Research. Currently, she actively serves multiple leadership roles within the American Statistical Association (ASA), which include: ASA Pittsburgh Chapter 2020 President-Elect, ASA Lifetime Data Science (LiDS) Section 2022 Program Chair-Elect, and ASA Statistical Partnership Across Academe, Industry & Government (SPAIG) Committee Vice Chair.