Routinely collected patient electronic medical record (EMR) data are approaching the genomic scale in volume and complexity and is increasingly recognized as a valuable resource for clinical research to answer questions for broader populations than would have ever been possible with a specialized research environment. However, the number of distinct clinical variables recorded in the EMR can easily go up to the thousands and most of these variables are not exploited in traditional predictive modeling as they typically deal with the complexity by selecting a limited number of commonly collected variables or clinician curated predictor variables. Machine learning can be an efficient approach to incorporate the entire EMR in identifying the important risk factors and effects of their interactions on diseases. In this presentation, Dr. Mei Liu will discuss how machine learning methods can facilitate EMR data-driven risk factor discovery for kidney disease.
After participating in this activity, the learner should be better able to:
- Learn how the machine learning methods can facilitate EMR data-driven risk factor discovery for kidney disease.
Mei Liu, PhD
University of Kansas Medical Center
Dr. Mei Liu is Assistant Professor of Medical Informatics in the Department of Internal Medicine at the University of Kansas Medical Center (KUMC). She received her PhD in
Computer Science from the University of Kansas and completed her postdoctoral training in Medical Informatics in the Department of Biomedical Informatics at Vanderbilt University.
At KUMC, she has been involved in building their clinical data repository for research as well as leading the data integration efforts for the Patient Centered Outcome Research Network
(PCORnet) Greater Plains Collaborative. Her current research interest is in developing machine learning methods for disease risk prediction and risk factor identification.