Reproductive Health Data Mining: Case Studies

This chapter focuses on case studies that demonstrate how approaches to data mining are used in the field of reproductive health practice and research. The focus of the chapter begins with an introduction to data mining tools and techniques which covers various aspects of several easy-to-use, free programs, such as WEKA (Waikato Environment for Knowledge Analysis), Rapid Miner, Knime, and Orange. This section discusses the pros and cons of each of these programs and their applications in the field. Further, the chapter discusses data mining pipelines and provides a general workflow for performing data mining on healthcare data. It further discusses the data mining algorithms commonly used in reproductive health research such as decision tree, random forest and support vector machines providing an example of these in research. In the final section of the chapter, two case studies are elaborated which provide a real-world illustration of the examples of data mining pipeline with reference to the reproductive health data.