Generally, my research lies in the development and evaluation of information system that utilize expert models but are specifically designed to improve the decision making of non-expert, or layperson, users. I am interested in bringing theory from behavioral decision making and behavioral economics to define new approaches for tailoring, displaying and interacting with information that are more effective in informing and motivating layperson users.

My most recent work focuses on the design and evaluation of personalized health web sites called health risk calculators for motivating user engagement, informed decision making and healthy behavior. I draw on theory and methods from risk communication and, more broadly, behavioral decision making to make personalized and interactive content more effective in capturing layperson users' attention, aligning their beliefs with expert models, and improving their decisions. I am also interested in the application of machine learning methods to the visualization of data for decision support. I have integrated existing dimensionality reduction methods with information visualization techniques to produce displays of health information databases that may aid health professionals in assessing chronic disease risk for a large patient population in the context of many disease risk factors.

Harle CA, Padman R, Downs J. The Impact of Web-Based Diabetes Risk Calculators on Information Processing and Risk Perceptions. Proceedings of the 2008 American Medical Informatics Association (AMIA) Annual Symposium, Washington, DC., 2008, Forthcoming.

“An Information Visualization Approach to Classification and Assessment of Diabetes Risk,” Poster Presented at Quality of Life Technology Center Expo, Pittsburgh, PA, April 12, 2007.

“Information Visualization and Meeting Physician Information Needs for Risk and Compliance Assessment,” Conference Presentation, INFORMS 2006, Pittsburgh, PA, Nov 5-8, 2006.