Predicting Maternal Health Care Seeking Pattern Using Data Mining Techniques in Ethiopia.
| dc.contributor.advisor | Jemaneh, Getachew | |
| dc.contributor.advisor | Mekonnen, Wubegzier (PhD) | |
| dc.contributor.author | Ayele, Dawit | |
| dc.date.accessioned | 2022-05-31T06:50:34Z | |
| dc.date.accessioned | 2023-11-05T15:16:04Z | |
| dc.date.available | 2022-05-31T06:50:34Z | |
| dc.date.available | 2023-11-05T15:16:04Z | |
| dc.date.issued | 2013-06 | |
| dc.description.abstract | Background: Utilization of maternal health care services could save unnecessary severe complications and death among women during pregnancy, delivery and after delivery. Ethiopia is one of the countries with high maternal morbidity and mortality in sub-Saharan Africa which needs more public health care effort in the country. Objective: The general objective of the study was to construct a model that can predict the maternal health care seeking pattern of reproductive age in Ethiopia. Methodology: The study followed Hybrid methodology of Knowledge Discovery Process to achieve the goal of building predictive model using data mining techniques. Therefore, the overall research design was to build a model that can predict the maternal health care seeking pattern using J48 Decision tree and Naïve Bayes algorithms in Ethiopia from EDHS 2011 dataset. WEKA 3.6.8 data mining tools and techniques were employed as a means to address the research problem. Results: The result of the study showed that the J48 Decision tree algorithm outperforms Naïve Bayes on the three of the outcome variables. For antenatal care the model was selected with an accuracy of 74.78%. Then for the second outcome variable (delivery care) the model was selected with an accuracy of 91.23% and area under receiver operating characteristics of 0.89. Finally for postnatal care the model was selected with an accuracy of 87.5% and area under receiver operating characteristics curve of 0.80. The best attributes selected for each of the outcome variables are Place of Residence, Household Wealth Index, Women’s Educational level, Husbands Occupation, Region, Husbands Educational level, Total number of children, Media Exposure. Conclusion: In general, the results obtained from this study were interesting and encouraging; it can be used as decision support for healthcare practitioner. The finding shows that there is a regional difference in utilizing maternal health care service in the country, thus it is recommended that all the concerned parties should give due consideration for these regions, increasing maternal education at least up to primary level in all regions of the country, provision of opportunities for employment and poverty reduction especially in rural parts of the region. | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/123456789/31820 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Maternal Health Care,Data Mining Techniques | en_US |
| dc.title | Predicting Maternal Health Care Seeking Pattern Using Data Mining Techniques in Ethiopia. | en_US |
| dc.type | Thesis | en_US |