Home // DBKDA 2013, The Fifth International Conference on Advances in Databases, Knowledge, and Data Applications // View article

An Epidemiological Data Mining Application Based on Census Databases

Authors:
Joaquín Pérez-Ortega
Crispín Zavala-Díaz
Alicia Martínez
Emmanuel Iturbide-Domínguez
Miguel Hidalgo-Reyes
Adriana Mexicano-Santoyo

Keywords: Data mining application; Mortality data; Census database

Abstract:
This paper shows the experience of a specialized data mining process that integrates mortality data collected by the official censuses of 2000 and 2010. The objective is the generation of patterns of interest based on the clustering of districts with high mortality rates for different causes of death. According to the specialized literature, few studies related to data mining applications using census databases have been reported, despite the potential census databases have. Contributions of this work are the implementation of a data preparation subsystem and the integration of a data warehouse that contains records of deaths, occurring in 2000 and 2010 for 2049 different causes of death. In order to validate the results, we analyzed four causes of death related to cancer C16 (stomach) and C34 (lung), and diabetes mellitus E11 (no insulin-dependent), and E14 (unspecified). Experimental results were satisfactory and they show some patterns of interest and an increase in the mortality rate in 2010 compared to 2000.

Pages: 217 to 223

Copyright: Copyright (c) IARIA, 2013

Publication date: January 27, 2013

Published in: conference

ISSN: 2308-4332

ISBN: 978-1-61208-247-9

Location: Seville, Spain

Dates: from January 27, 2013 to February 1, 2013