Determinants of Immunization Among Children Aged 12-23 Months in Ethiopia: A Proportional Odds Model Approach
Pages 140-155
Mesay Tefera and M.K. Sharma
DOI: http://dx.doi.org/10.6000/1929-6029.2014.03.01.15
Published: 16 February 2015

Abstract: Childhood immunization is recognized as one of the most cost-effective public health interventions to prevent morbidity and mortality caused by infectious diseases, particularly in a high-endemic setting. According to the 2011 EDHS report by the Central Statistical Agency (CSA) of Ethiopia, nationally, only 24 percent of children age 12-23 months was fully immunized at the time of the survey. The main objective of this study was to identify and describe the determinants of immunization among children aged 12-23 months in Ethiopia. The source of the data was the Ethiopian Demographic and Health Survey conducted in 2011 (EDHS) 2011. In order to meet our objectives descriptive, and ordinal logistic regression (proportional odds model) statistical techniques were used for data analysis using socio-economic and demographic variables as explanatory variables and immunization status of children aged 12-23 months as the response variable. The results of the analysis predicts that place of delivery, wealth index, possession of radio and region were found to be significant determinants for full immunization among children aged 12-23 months in Ethiopia.

Determinants of Wasting Among Under-Five Children in Ethiopia: (A Multilevel Logistic Regression Model Approach)
Pages 368-377
Gutu Adugna Dabale and M.K Sharma
DOI: http://dx.doi.org/10.6000/1929-6029.2014.03.04.5
Published: 06 November 2014

Abstract: Child malnutrition in Ethiopia is one of the most serious public health problems and the highest in the world. Wasting refers to low weight-for-height and measures the body’s mass in relation to body length. The objective of this study was to identify determinants of wasting among under-five children in Ethiopia. The study used data collected in the Ethiopian Demographic and Health Survey in 2010/2011. A total of 9611 under-five age children were included in the present study. To analyze the data descriptive statistics and multilevel binary logistic regression techniques were employed. The descriptive statistics results indicate that about 11.7 % of under-five children in Ethiopia were wasted. The results of study indicated that the risk of wasting was highest among male children, small size at birth, children whose parents resided in rural areas, children’s of illiterate mothers, children whose mother’s body mass index was low, children from poor families and children who had diarrhea and fever two weeks before the date of the survey. The multilevel model also showed the existence of significant variations in the prevalence of wasting among the regions in Ethiopia.

Determinants of Utilization of Maternal Healthcare Services in Ethiopia
Pages 378-390
Wondiber Nega Melese, Shirnevas Darak and Mesay Tefera
DOI: http://dx.doi.org/10.6000/1929-6029.2015.04.04.7
Published: 03 November 2015

Abstract: Utilizing maternal healthcare services, such as antenatal care, professionals’ assistance during delivery and postnatal care contributes significant role in reduction of maternal and child mortality. However, there are many factors both at individual and community level that affect utilization of these required services. To determine the levels of effects of socio-economic and demographic factors on uses of Maternal Healthcare services 7764 women who had given birth at least one times have taken from the 2011 Ethiopian DHS. The results showed that the rate of safe motherhood practices among reproductive age group of women in Ethiopia were too low. About 51 percent of them did not use any health care services during pregnancy, childbirth, and post-delivery periods. As WHO recommend only 6.9 percent of women were attending ANC at least four times, assisted by health professional during delivery and received PNC. The result of logistic regression showed that antenatal care, skilled delivery and postnatal care utilizations were commonly influenced by place of residence, wealth status, women’s and husband’s education and parity. Whereas, mother’s working status and husband’s education were found to be uniquely influence the uses of ANC and PNC services, respectively. In addition, both religious affiliation and age of women were also prominent predictors on utilization of ANC and uses of skilled assistance during delivery. Based on these significant factors, it is important to design and promote uses of maternal healthcare services in order to minimize the risk of maternal and child mortality.

Development of Predictive Models for Continuous Flow Left Ventricular Assist Device Patients using Bayesian Networks
Pages 423-434
Natasha A. Loghmanpour, Manreet K. Kanwar, Raymond L. Benza, Srinivas Murali and James F. Antaki
DOI: http://dx.doi.org/10.6000/1929-6029.2014.03.04.11
Published: 06 November 2014

Abstract: Background:Existing prognostic tools for patient selection for ventricular assist devices (VADs) such as the Destination Therapy Risk Score (DTRS) and newly published HeartMate II Risk Score (HMRS) have limited predictive ability, especially with the current generation of continuous flow VADs (cfVADs). This study aims to use a modern machine learning approach, employing Bayesian Networks (BNs), which overcomes some of the limitations of traditional statistical methods.

Methods:Retrospective data from 144 patients at Allegheny General Hospital and Integris Health System from 2007 to 2011 were analyzed. 43 data elements were grouped into four sets: demographics, laboratory tests, hemodynamics, and medications. Patients were stratified by survival at 90 days post LVAD.

Results:The independent variables were ranked based on their predictive power and reduced to an optimal set of 10: hematocrit, aspartate aminotransferase, age, heart rate, transpulmonary gradient, mean pulmonary artery pressure, use of diuretics, platelet count, blood urea nitrogen and hemoglobin. Two BNs, Naïve Bayes (NB) and Tree-Augmented Naïve Bayes (TAN) outperformed the DTRS in identifying low risk patients (specificity: 91% and 93% vs. 78%) and outperformed HMRS predictions of high risk patients (sensitivity: 80% and 60% vs. 25%). Both models were more accurate than DTRS and HMRS (90% vs. 73% and 84%), Kappa (NB: 0.56 TAN: 0.48, DTRS: 0.14, HMRS: 0.22), and AUC (NB: 80%, TAN: 84%, DTRS: 59%, HMRS: 59%).

Conclusion:The Bayesian Network models developed in this study consistently outperformed the DTRS and HMRS on all metrics. An added advantage is their intuitive graphical structure that closely mimics natural reasoning patterns. This warrants further investigation with an expanded patient cohort, and inclusion of adverse event outcomes.