Introduction to Big Data for Health is a new elective course intended to introduce students to the many types of data and analytical methods now available that will enhance our ability to investigate and explain the health of communities. These include data that are relevant to measurement of the social economic and genetic determinants of health, the quality and outcomes of healthcare programs and healthcare interventions. The quantity and variety of relevant data have increased substantially in the last decade and now include data from: healthcare administration, electronic medical records, diagnostic laboratories, censuses, vital statistics, environmental exposures, disease and device registries, research data-bases and bio-repositories. To this may be added relevant information extracted from social services, taxation records, education, justice and corrections services. This is a rapidly changing field. The aims of the course are to introduce students to the different types of data, to provide an overview of the different analytical approaches and to assess the potential value of these big data -sets by examining a number of examples of their use.
The aims of the course are to provide students with an overview of the different types of data, the different analytical approaches and to assess the potential value of these big data-sets by examining a number of examples of their use.
Taxonomy of health data, characteristics of structured and unstructured health data.
The value of individually linked data.
Different analytic approaches to ‘wide’ and ‘deep’ data.
Data security and privacy, data sharing, de-identification and governance.
Working with distributed data networks.
Examples of the use of big data in health and healthcare.
Examples of the use of big data in policy evaluation.