Zhen Chen, Ph.D.

Machine learning, exposure mixtures, and diagnostic accuracy - methods development and applications to perinatal epidemiology

My main research interests are in machine learning, exposure mixtures, and diagnostic accuracy, with applications to perinatal epidemiology. In many epidemiological studies, an index might be an efficient and parsimonious way to capture the effect of a group of exposures (exposure mixture) . In these cases, my group has been developing Bayesian additive regression tree based approaches that allow heterogeneity of the effect of an index. My group also is exploring machine learning and artificial intelligence methods for the purpose of predicting birthweight. Improved prediction of birthweight has great implication in managing delivery of fetuses that are too big and taking preventive measures for fetuses that are too small. In diagnostic accuracy, my group has continued in ROC curve modeling under various constraints.

Dr. Chen is a senior investigator in the Biostatistics and Bioinformatics Branch at NICHD. He obtained his Ph.D. in statistics in 2001 at University of Connecticut, and was a Research Fellow at NIEHS from 2001 to 2003. He served as an Assistant Professor (Clinical Educator track) in the Department of Biostatistics and Epidemiology at the University of Pennsylvania from 2003 to 2008 and joined NICHD as a Staff Scientist in 2008 before becoming an investigator in 2009.