A Case Study on Disease Diagnosis Using Gene Expression Data Classification with Feature Selection: Application of Data Science Techniques in Health Care

Abstract

A large volume of data is being generated in the health care field. The use of data science techniques can unveil useful information that is very difficult to find otherwise because traditional computational techniques are not able to process and handle the huge amount of data. This chapter introduces various application areas where data science can be useful to analyze health care data. This chapter also discusses various issues and challenges faced by data scientists during the knowledge discovery process. Feature engineering techniques that can solve these issues are also exhibited here. A case study of gene classification with binary particle swarm optimization (BPSO)–based feature selection technique is presented in detail in order to give a detailed understanding of how things actually work. Moreover, the references to open-source code and datasets are shared so that the readers can explore different techniques on their own. After reading this chapter, the reader will perceive information about different applications of data science techniques in the health care field and discover the issues and challenges related to it. The reader will get to know various feature selection techniques and comprehend the gene classification application.