David Gotz spoke on various efforts from the “The Visual Analytics and Communication Lab,” which conducts research at the intersection of interactive visualization, human-computer interaction, and machine learning. Key research questions from the VACLab include how to make exploratory discoveries and visualizations from the large volume of complex data available to us and what new visual analytics methods need to be created to complete this task more efficiently. The first set of projects he shared involved applying visual analytics for temporal event data in population health — visualizing patient trajectories that capture health event patterns from both electronic health data collected by medical professionals with patient-generated data outside of the office.The second project set centered around countering bias when researchers explore complex data, including identifying the the origin and effects of bias, creating methods to mitigate the effects and improve the quality of data analysis, and testing the methods in real-world scenarios. Additionally, Gotz spoke on applying several of the lab’s project work to the COVID-19 pandemic, including sharing population health research, assisting the North Carolina Department of Health and Human Services with data dashboards, and engaging the public with research findings to encourage behavioral change. Click here to view the talk on YouTube.
David Gotz | Department BioMcColl Term Professor, School of Information and Library Science
Featured on: June 23, 2022 (Event Page)
Session Title: Data Science: More than Numbers (Event Recap)
Tools, Information, and Resources:
- CHIP (Carolina Health Informatics Program): The Carolina Health Informatics Program (CHIP) is an interdisciplinary research and training program that plays a key role in fulfilling UNC-Chapel Hill's commitment to improving human health through health informatics research, data sharing, development, and education.
- VACLab (Visual Analysis and Communications Laboratory): The Visual Analysis and Communication Laboratory (VACLab) conducts research at the intersection of interactive visualization, human-computer interaction, and machine learning. Led by Dr. David Gotz, the VACLab develops new methods of interactive visualization to support more efficient, effective, and intuitive information analysis and communication. Some notable projects include:
- Combating Bias via Contextual Visualization: Research projects within this theme examine and evaluate new visual analytics methods that aim to reduce threats to validity that arise from various bias effects during exploratory visual analysis.
- Visualizing the COVID-19 Outbreak: An interactive visualization of live data about the COVID-19 outbreak across the United States.
- Population Health Methods and Tools: Projects that aim to visualize patient trajectories that capture health event patterns from millions of people.
- Apache cTAKES™: A natural language processing system for extraction of information from electronic medical record clinical free-text.