Browsing by Author "Abebe, Hiwot"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Indoor Air Bacterial Load and Contributing Factors in Government and Private Hospitals in Harar, Harar Town, Eastern Ethiopia
    (Addis Ababa University, 2017-06) Abebe, Hiwot; Kumie, Abera (PhD)
    Background: Human can be exposed to airborne microorganisms in both residential and hospital indoor environments. This may lead to adverse health effects with major public health impacts. Hospital indoor air may contain a vast number of disease causing agents that could be originate from patients, the staff, visitors, ventilation and outdoors. Hospitalized patients are at a higher risk of infection due to confined spaces that can accumulate microorganisms and create favorable condition for their growth and multiplication. Objectives: to determine and compare indoor bacterial load, and contributing factors in different wards of the four hospitals in Harar town, 2017. Methods: A cross sectional study design was used to assess the bacterial load and associated factors in two government hospitals (Police and Jugula), one teaching hospital (Hiwot-Fana) and one private hospital (Yemage) in Harar town. Nine inpatient wards and 96 rooms were taken as a sample to determine the bacterial load. All of the impatient rooms of all wards of these hospitals were included in the study. To determine the bacterial load of these rooms’ passive air sampling technique was used. Data was collected using settle plate method by exposing petridish of blood agar media for an hour to the indoor air of the sampled rooms. Observation checklist was used to assess the contributing factors that influence the quality of the indoor air. Results; Based on our finding, airborne bacteria load ranged from 74.2–14,310 CFU/m3. The highest bacterial load was found in medical ward and the lowest in OR of Hiwot-Fana specialized teaching hospital. The result of one-way ANOVA showed a significant difference in mean bacterial load among the four hospitals and also the major wards of these four hospitals. In those hospitals, S.aureus, micrococcus and CoNS were among the most common bacteria identified. This study suggests that cleaning frequency, room temperature, a high number of health and medical students as well as number of visitors were found to be determinants that affect bacterial load in the sampled rooms. Conclusion: High bacterial load was recorded in Jugula, Police & Hiwot-Fana specialized teaching hospitals. The bacterial load of Hiwot-Fana specialized teaching hospital was much higher the other hospitals. Environmental factors play a major role in the increase of bacterial load. Thus, this high bacterial load in those hospitals may lead to high infection risk to the admitted patients.
  • No Thumbnail Available
    Item
    Predicting Infant Immunization Status in Ethiopian: The Case of Ethiopia Demographic and Health Survey 2011
    (Addis Ababa University, 2014-06) Abebe, Hiwot; Meshesha, Million (PhD); Mekonnen, Wubegzier (PhD)
    Background: Immunization is one of the most cost effective and efficient interventions saving the lives of many millions of infants and children from dying of infectious and preventable diseases. In 2007, approximately 27 million infants are not vaccinated against common childhood diseases and 2–3 million children are dying annually from easily preventable diseases and many more fall ill. Objective: The research has a general objective of construct a predictive model using data mining technology that helps to predict the infants’ immunization status in Ethiopia. The result of the study is expected to be important for different parties such as infants, health professionals, policy makers, programmers and researchers. Methodology: This study is guided by a Hybrid-data mining model which is a six step knowledge discovery process model such as understanding of the problem, understanding of the data, preparation of the data, data mining, and evaluation of the discovered knowledge and use of the discovered knowledge. The study has used 8,210 instances, 12 predicting and one outcome variables to run the experiments. Due to the nature of the problem and attributes contained in the dataset, classification data mining task is selected to build the classifier models. The mining algorithms; J48 decision tree, sequence minimal optimization support vector machine, multilayer perceptron neural network and partial decision tree rule induction are used in all experiment due to their popularity in recent related works. Ten-fold cross validation technique is used to train and test the classifier models. Performance of the models is compared using accuracy, true positive rate, false positive rate, and the area under the Receiver Operating Characteristics curve. Result: The J48 decision tree has given the best classification and a better predictive accuracy of the infant immunization status in Ethiopia. The experiment has generated a model with accuracy of 62.5%, weighted precision of 62.5% and weighted ROC area of 67.6% for the J48 decision tree. And if place of delivery = home region = Affar AND mother-education-level = no-education AND wealth-status = poor AND listening-to-radio = not-at-all AND mother-age = 25-29 AND parity = 6-7 then Unimmunised (10.0/1.0).Therefore, increase awareness creation among women in pastoralist communities so as to enhance vaccine coverage. Conclusion: The results achieved from this research indicate that data mining is useful in bringing relevant information from large and complex EDHS dataset, and we can this information for predicting infant immunization status and decision making. The most important attributes that determine infant immunization status were place of delivery, region, mother's educational level, listening to radio, father education level, residence, mother age, wealth status, parity, distance to health facility and marital status.
  • No Thumbnail Available
    Item
    Predicting Infant Immunization Status in Ethiopian: The Case of Ethiopia Demographic and Health Survey 2011.
    (Addis Abeba University, 2014-06) Abebe, Hiwot; Meshesha, Million(PhD); Mekonnen, Wubegzier(PhD)
    Background: Immunization is one of the most cost effective and efficient interventions saving the lives of many millions of infants and children from dying of infectious and preventable diseases. In 2007, approximately 27 million infants are not vaccinated against common childhood diseases and 2–3 million children are dying annually from easily preventable diseases and many more fall ill. Objective: The research has a general objective of construct a predictive model using data mining technology that helps to predict the infants’ immunization status in Ethiopia. The result of the study is expected to be important for different parties such as infants, health professionals, policy makers, programmers and researchers. Methodology: This study is guided by a Hybrid-data mining model which is a six step knowledge discovery process model such as understanding of the problem, understanding of the data, preparation of the data, data mining, and evaluation of the discovered knowledge and use of the discovered knowledge. The study has used 8,210 instances, 12 predicting and one outcome variables to run the experiments.Due to the nature of the problem and attributes contained in the dataset, classification data mining task is selected to build the classifier models. The mining algorithms; J48 decision tree, sequence minimal optimization support vector machine, multilayer perceptron neural network and partial decision tree rule induction are used in all experiment due to their popularity in recent related works. Ten-fold cross validation technique is used to train and test the classifier models. Performance of the models is compared using accuracy, true positive rate, false positive rate, and the area under the Receiver Operating Characteristics curve. Result: The J48 decision tree has given the best classification and a better predictive accuracy of the infant immunization status in Ethiopia. The experiment has generated a model with accuracy of 62.5%, weighted precision of 62.5% and weighted ROC area of 67.6% for the J48 decision tree. And if place of delivery = home region = Affar AND mother-education-level = noeducation AND wealth-status=poor AND listening-to-radio=not-at-all AND mother-age=2529 AND parity = 6-7 then Unimmunised (10.0/1.0)wherefore, increase awareness creation among women in pastoralist communities so as to enhance vaccine coverage. Conclusion: The results achieved from this research indicate that data mining is useful in bringing relevant information from large and complex EDHS dataset, and we can this information for predicting infant immunization status and decision making. The most important attributes that determine infant immunization status were place of delivery, region, mother's educational level, listening to radio, father education level, residence, mother age, wealth status, parity, distance to health facility and marital status.