Use of data mining technique to monitor novel corona virus (COVID-19) infections in Gujarat, India.

District-based health care development and guidelines necessitate grouping affected areas due to novel corona virus (COVID-19) into regions of similar severity. In this study, the grouping is focused on districts in the state Gujarat, India in the context of COVID-19 infections. The state government, health ministry, doctors etc. are facing lots of difficulties how to identify regions and to group them depending upon their similarities. Data mining is one of the techniques which deal with a process to uncover hidden features of big data. In the current study, we apply cluster analysis, one of the data mining techniques for the purpose. The main objective of the results of clustering in this study is to develop and to optimize monitoring techniques in various regions of the state Gujarat to a level of severity of the infections. And thus the study will be very valuable for the policy makers, the state government, district governments, health care professionals who are delivering services to hospitals, doctors, the police and others involved in understanding seriousness of the spread of novel corona virus (COVID-19) so that they could plan at a district level need such as number of doctors, nurses, beds, ventilators, testing kits, masks and other facilities. Such study will also be helpful in reducing total number of infected persons, daily new cases as well as in increasing the number of recovered patients so that number of deceased persons could be reduced. [ABSTRACT FROM AUTHOR]