Uma análise sobre as doenças prevalentes na população da cidade de Ipanguaçu/RN a partir do processo ETL

Abstract

In the last decade, the need for an automated process for the discovery of relevant information involving large volumes of data has increased, however, several organizations have generated it digitally, this information being fundamental for managers and administrators to seek results that are being generated by their employees’ services themselves. In the hospital environment, data are still stored physically, such as in Basic Health Units (UBS), which can generate several inconsistencies and increase the difficulty for further analysis of these data. Thus, the motivation of this work is a problem that converges to an articulation between information technology and health, with the aim of analyzing the diseases prevalent in the population of the city of Ipanguaçu / RN through data collections. The methodology used was the quantitative approach, which was divided into 3 stages: ETL process, data mining stage using Excel software, knowledge discovery process (KDD) and the analysis of results using the inductive method. Based on the results obtained, it was possible to identify the most prevalent diseases in the months of July and August of 2018.