|
Abstract:
|
Most contemporary scientific inquiries rely on massive amounts of data and demand substantial trans-disciplinary 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 trans-disciplinary advances, technological innovation and effective mechanisms for managing and interrogating Big Data. However, 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.
|
