Speakers: Kangwon Seo, PhD

Kangwon Seo, PhD

 

Assistant Professor
Industrial and Manufacturing Systems Engineering; Statistics
University of Missouri

 

Dr. Seo is an assistant professor in the Department of Industrial and Manufacturing Systems Engineering (IMSE) and the Department of Statistics at the University of Missouri (MU). His primary research interest includes applied statistics, experimental design for non-normal response data such as failure time data from reliability tests, and large-scale data analytics in the application of healthcare. From one of his previous research, he developed a visualization tool for Alzheimer’s disease (AD) progression path, where critical measurements for classifying the normal and AD patients were identified from brain images and visualized in an intuitive way using dimension reduction techniques. He is currently working on a project of nurses’ EMR dashboard development with undergraduate students in MU IMSE.

Dashboards to Visualize ICU Nurses’ EMR Log Data

It is critical to monitor the physical and mental workloads of nurses to detect potential risks of human errors involved in healthcare service. Several studies show that the use of the electronic medical records (EMR) system is one of the leading sources that is highly associated with nurses’ workloads. While nurses’ EMR usage pattern may provide valuable sources to guide their workload statuses, it is not an easy task to extract useful information from EMR event log data due to its unstructured data collection protocol and large data size. In this project, we develop an automated system to manipulate the raw EMR event log data, extract nurses’ EMR usage profiles, and dashboard for visualization and monitoring. To do this, nurses’ EMR system event log data collected from the intensive care unit (ICU) of the University of Missouri (MU) Hospital will be obtained. Then, the target EMR metrics and profiles that are expected to be potentially associated with a nurse’s workload are defined. Using an open-source software such as R Shiny, data extraction and manipulation programs will be developed. As an outcome, the EMR profile dashboard, which provides an intuitive visualization of a nurse’s EMR usage behavior, will be developed.