Uncovering Knowledge That Supports Malaria Prevention and Control Intervention Program in Ethiopia
No Thumbnail Available
Date
2011-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Malaria is one of the leading causes of death in Ethiopia. Though there are many efforts
to control malaria, the complexity of the problems is still very severe. So there is a need
to investigate in detail the synergic effect of risk factors with temperature, altitude, type
of visit and malaria type and their causes of death. Hence in this research an attempt is
made to determine the hierarchical importance of different risk factors and their patterns
on malaria death occurrence.
In this study, knowledge discovery techniques are evaluated to support and uncover
knowledge to scale up the malaria prevention and intervention program in Ethiopia.
CRISP methodology with classification algorithms such as J48, JRip and MLP and
pattern discovery analysis techniques like Apriori adopted to uncover knowledge for the
mining of interesting rule from total datasets of 37, 609 records. An attempt is made to
preprocess the data using business and data understanding with detail statistical summary
in order to fill missing and detect noisy value. Essential target dataset attributes have
been constructed by integrating WHO malaria databases, National Metrological data and
National Mapping Data.
All classification techniques discover important attributes/factors that determine the
malaria type of cases and occurrence of deaths. J48 Decision tree and MLP correctly
classify 95.9% and 97.4%, respectively to predict occurrence of death. The findings of
this rsearch indicate that rainfall is the significant factor that determines the prevalence of
malaria. When the number of malaria cases increases there is a probability of death
occurrences; the risk is relatively high with those less than 5 years age. In most zones,
malaria transmission rate is high from May to January because of favorable climate
conditions for malaria reproduction.
Apriori techniques (both general and class association mining) also strengthen the result
of J48 and MLP. More interestingly, it discovers occurrence of death, mostly related with
severe anemia cases rather than pregnancy cases. Such interesting rule needs further
investigation to validate.
Description
Keywords
Uncovering Knowledge That Supports Malaria Prevention