Applications of Big Data Science and Analytic Techniques for Health Disparities Research

Abstract

In recent years we have seen a dramatic increase in health-related data resulting in enormous data sets and sources, typically described as big data. Within the National Institutes of Health, big data refers to the complexity, challenges, and new opportunities presented by the combined analysis of diverse, multimodal, and unstructured data, usually with data volumes greater than one terabyte. Big data science, as it applies to precision medicine, is the generation and storage of large amounts of data from biospecimens, health records, medical imaging, and sensors from which disease-specific factors, patterns, and associations can be computationally identified and used to generate insights for clinical care, decision making, and treatment. In the broad sense, it includes electronic health records, biologic data (genomics, proteomics, metabolomics), environmental and lifestyle data, and data from wearable technology and mobile phone applications. This chapter will discuss the foundations of big data, big data analytics, and opportunities for conducting health disparities research.