Patient deep phenotyping from various data types in electronic health records; phenotype- and genomic-based disease modeling and algorithm development for translational research and differential diagnoses
Xingmin “Aaron” Zhang, Ph.D. received his doctorate of philosophy in the Cellular & Molecular Biology Program at the University of Wisconsin-Madison in summer 2017. He identified and characterized novel genes that participate in regulated dense core vesicle exocytosis, a cellular process that controls many essential events such as insulin secretion, synaptic transmission and immune responses, through a combination of data driven and web lab-based methods. Dr. Zhang developed a particular interest in combining his training in cell biology and his computational skills to study human diseases. Following his graduation, Dr. Zhang joined the Robinson’s lab as a postdoc to develop computational tools & algorithms for analyzing data from electronic health records (EHR). Dr. Zhang led the LOINC2HPO project that aims at extracting patient phenotypes from clinical laboratory tests in EHR for medical research and differential diagnoses. Dr. Zhang is currently working on harmonizing other data types in EHR and combining genomic information to develop novel algorithms and statistical models to improve human disease diagnoses.
There has been an explosion of digital medical data in recent years, taking many forms. Much of the most valuable data—clinical patient data—is currently stored in electronic health record (EHR) systems, providing a theoretical gold mine for large-scale integration and analyses of patient traits, diseases, treatments, progression over time, outcomes and more.