ABSTRACT
This chapter provides better understanding about healthcare data and its different forms with some possible algorithms and uses cases. It examines the data variability and focuses on data collection. The chapter describes the structured data, the semi-structured data and explains the unstructured data. Structured data are organized or labeled data that can be analyzed easily and effectively. They are well organized data that are formatted in a repository such as a database. Semi-structured data are structured data formed in an unorganized way. This type of data has the properties related to an organization but will not reside in the relational database and can be processed easily. The data that is in unorganized formats or that do not have data models are said to be unstructured data. Data collection is defined as the process of collecting, analyzing, and interpreting different types of information relating to a particular disease or healthcare need.
