Big Data Analytics in E-Healthcare Using Hadoop and Hive

New technologies like big data, cloud computing, machine learning could play a vital role in providing healthcare services to patients. The healthcare industry is producing a large volume of data which is increasing exponentially. Healthcare industry data is unstructured and is collected in different varieties. There is a dire need of processing these huge volumes of healthcare datasets to provide personalized treatment to the patients, to provide predictive analytics so the pre-diagnosis can take place. To predict the insights from existing patient data requires new tools and techniques as healthcare data is complex. Big data technologies such as Hadoop, MapReduce, Pig, Hive, and others provide the platform for healthcare data processing. Increasing rates of severe health diseases are impacting human life. One such kind of disease is cancer, this work presents the association between smoking and lung cancer. This paper presents the implementation of hive architecture for analyzing the lung cancer rate among active smokers dataset from centers of disease control and prevention government agency. The results obtained show that active smokers have a higher rate of lung cancer. It also addresses various challenges of implementing big data techniques over healthcare data.