Introduction to use of Structured Medical Record Data

Electronic medical record (EMR) data is encoded in patient charts through the course of clinical care and subsequent patient billing. Coded data in the electronic records (such as information stored as ICD/CPT/LOINC/RxNorm codes) provide vast amounts of valuable patient data. However, effectively applying data science tools to EMR data requires understanding dataset limitations and avoiding common false assumptions. Johanna will address these considerations as she introduces some Common Data Models, cohort exploration tools, and CTSA-related resources. The National COVID Cohort Collaborative Stroke will be used to demonstrate approaches to structured health data.

Johanna has a degree in Symbolic Systems: Neural Systems from Stanford University and a master’s in Systems Engineering from the University of Virginia. Johanna has extensive clinical research experience and previously served as the Director of Neurosurgery and Neuro-oncology Clinical Research for the University of Virginia. In her current role with iTHRIV, Johanna is the Director of the iTHRIV Informatics Core, a cross-state team working to accelerate health research by facilitating data transfer and linking and analysis in a secure environment. In addition to designing systems that support all of the iTHRIV service lines, Johanna provides personal consults to health researchers on project design and implementation, including plans for data collection, management, and analysis.

Learning Objectives
Introduction of Common Data Models, cohort exploration tools, and CTSA-related resources.

Scientific concepts and research design
Data management and informatics

University of Virginia

Time Required
1 hour


On demand

Delivery Method