Interactive Ensemble Clustering for Mixed Data with Application to Mood Disorders

• Activity Number: 528
• Type: Topic Contributed
• Date/Time: Wednesday, August 3, 2016 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Ellen Eischen* and David Gotz and Rachael Hageman Blair and Arianna Di Florio and Mathews Jacob and Brian Chapman
• Companies: University of Oregon and The University of North Carolina at Chapel Hill and University of Buffalo and The University of North Carolina at Chapel Hill and University of Iowa and University of Utah

Abstract

This interdisciplinary project is exploring novel data science methods to improve classification and diagnosis of mood disorders, in particular bipolar disorder and major depressive disorder. The key objective is to lay the groundwork for a long term program that includes the creation of data-driven visualization tools to assist clinicians with diagnosis of mood disorders. The psychiatric community has recognized the critical need for a more precise, evidence-based approach for the diagnosis and treatment of disease. This project is motivated by the hypothesis that a more precise and personalized classification of mental health disease can be obtained through the development of novel clustering methods that identify clinically significant structures with large population data sets. Despite the focus on mood disorders, the framework is generalizable to other diseases (such as obesity-related diseases) that face similar challenges for diagnosis and treatment.