Translational biomedical research relies on massive amounts of heterogeneous data and demands substantial transdisciplinary expertise to extract valuable information and acquire new knowledge about complex natural process. The Moore’s and Kryder’s laws guarantee exponential increase of computational power and information storage, respectively. These laws also dictate the rapid transdisciplinary advances, technological innovation and effective mechanisms for managing and interrogating Big Data. Evidence from neuroimaging, clinical, and genetics studies suggests the rate of increase of data outpaces our ability to process it completely, effectively, and consistently. We will discuss the 6 defining characteristics of Big, Deep, and Dark Data (size, incongruency, incompleteness, multi-scales, complexity, and multi-sourceness) in relation to Big Healthcare Data. Applications will include demonstrations of predictive Big Data analytics based on complex Alzheimer’s and Parkinson’s studies. A spectrum of Big Data computational barriers, knowledge gaps, scientific challenges, and training opportunities will be presented.
After participating in this activity, the learner should be better able to:
- Describe characteristics of big data and their associated challenges in relation to healthcare.
- Outline methods that integrate and extract knowledge from clinical, imaging and genomic data sources.
- Identify resources and training opportunities in the area of neuroimaging and big data computation.
- Illustrate how these methods have yielded new insights into the etiology of Alzheimer’s and Parkinson’s diseases.
Ivo Dinov PhD
Associate Professor of Health Behavior and Biological Sciences
University of Michigan
Dr. Ivo Dinov (http://umich.edu/~dinov) is an associate professor of Health Behavior and Biological Sciences at the University of Michigan. He directs the Statistics Online Computational Resource (www.SOCR.umich.edu), which has over 10.4 million visitors worldwide since 2002. He is an expert in mathematical modeling, statistical analysis, computational processing and scientific visualization of large datasets (Big Data). Dr. Dinov is involved in longitudinal morphometric studies of human development (e.g., Autism, Schizophrenia), maturation (e.g., depression, pain) and aging (e.g., Alzheimer’s disease, Parkinson’s disease). He is an associate education director of the Michigan Institute for Data Science (MIDAS), co-directs the Center for Complexity and Self-management of Chronic Disease (CSCD), and co-directs the multi-institutional Probability Distributome Project.