University of Kentucky
Internal Medicine and Computer Science
Abstract: Data harmonization is vital for data-driven large-scale healthcare data analysis. Effective clinical decisions require the collection, modeling, and interpretation of large-scale healthcare data, including medication records, genomic sequences, clinical notes, and medical images. However, the design of the EHR system is not meant for clinical data analysis tasks. In particular, the application of non-standardized imaging protocols poses a fundamental challenge to extract valuable information and gain actionable knowledge from medical images. In the last two years, the Chen lab has developed a set of image harmonization algorithms to learn the data distribution of training images and generate synthesized images under the same distribution. The tools can be modified for scientific data harmonization and preprocessing.
Bio: Dr. Jin Chen is an associate professor in the Department of Internal Medicine and Department of Computer Science, University of Kentucky. He obtained his BE and PhD in Computer Science from Southeast University, China, and National University of Singapore, Singapore in 1997 and 2007 respectively. In between, he has worked as a software engineer for 5 years. Prior to joining UK, Dr. Chen was a research associate at the Carnegie Institution for Science, Stanford, and an assistant professor in the Department of Energy Plant Research Laboratory and Department of Computer Science and Engineering, Michigan State University. Dr. Chen's research focuses on the development of AI algorithms to solve problems in medical and biological informatics, including inter-functional clustering, transient pattern identification, ontology development, data quality control, and data visualization. He has authored and co-authored more than 100 papers and received support from NIH and NSF.