Predicting the Pattern of Under-five Mortality in Ethiopia Using Data Mining Technology: The Case of Butajira Rural Health Program.

No Thumbnail Available

Date

2012-06

Journal Title

Journal ISSN

Volume Title

Publisher

Addis Ababa University

Abstract

Introduction:The under-five deaths in Ethiopiarepresent 48% of all mortality. More than halfof the under-five deaths occurred during the first year of life, and 53% of these before 2 monthsof age.Data miningis a collection of techniques for efficient automated discovery of previouslyunknown, valid, novel, useful and understandable patterns in large databases. Objective:The main objective of this study is to explore the potential applicability of datamining to predict the determinants, levels and pattern of under-five mortality in Ethiopia,particularly for the Butajira rural health program sites. This can greatly support for policymakers, planners, and healthcare providers working on the control of under-five childrenmortality in Ethiopia. Methods andMaterial:The methodology used for this research was a hybrid six-step CiosKnowledge Discovery Process. The required data was collected from Butajira rural healthprogramdatabase covering the period 1987-2008. The researcher used two popular data miningalgorithms (C4.5 J48 Decision Trees and Naïve Bayes Classifier) to develop the predictivemodel using a larger dataset (11,600 cases). The researcher also used a 10-fold cross validationand 90% split test mode fordataminingmethods of the two predictive models for performancecomparison purposes. Results:The results indicated that the decision tree (J48algorithm) is the best predictor withpruned parameter of the tree of 90% split test mode; it has 97.49% accuracy on the holdoutdataset (this predictive accuracy is better than any reported in the literature), Naïve BayesClassifier came out to be the second with supervised discretization has 96.67% accuracy. Conclusion:The results from this study were very capable and confirmed the belief thatapplyingdata mining techniques could indeed support a predictive model building task thatpredicts the pattern of under-five mortality in Ethiopia; particularly for Butajira rural healthprogramsitesarepossible. In the future, more classification studies by using a possible largeamount ofButajira rural health programdemographic and surveillance sitesdataset records withepidemiological information and employing other classification algorithms, tools and techniquescouldyield better results.

Description

Keywords

Under Five Mortality ,Data Mining Technology

Citation