Interpretable prediction of acute respiratory infection disease among under-five children in Ethiopia using ensemble machine learning and Shapley additive explanations (SHAP).

Background: Although the prevalence of childhood illnesses has significantly decreased, acute respiratory infections continue to be the leading cause of death and disease among children in low- and middle-income countries. Seven percent of children under five experienced symptoms in the two weeks preceding the Ethiopian demographic and health survey. Hence, this study aimed to identify interpretable predicting factors of acute respiratory infection disease among under-five children in Ethiopia using machine learning analysis techniques. Methods: Secondary data analysis was performed using 2016 Ethiopian demographic and health survey data. Data were extracted using STATA and imported into Jupyter Notebook for further analysis. The presence of acute respiratory infection in a child under the age of 5 was the outcome variable, categorized as yes and no. Five ensemble boosting machine learning algorithms such as adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), Gradient Boost, CatBoost, and light gradient-boosting machine (LightGBM) were employed on a total sample of 10,641 children under the age of 5. The Shapley additive explanations technique was used to identify the important features and effects of each feature driving the prediction. Results: The XGBoost model achieved an accuracy of 79.3%, an F1 score of 78.4%, a recall of 78.3%, a precision of 81.7%, and a receiver operating curve area under the curve of 86.1% after model optimization. Child age (month), history of diarrhea, number of living children, duration of breastfeeding, and mother's occupation were the top predicting factors of acute respiratory infection among children under the age of 5 in Ethiopia. Conclusion: The XGBoost classifier was the best predictive model with improved performance, and predicting factors of acute respiratory infection were identified with the help of the Shapely additive explanation. The findings of this study can help policymakers and stakeholders understand the decision-making process for acute respiratory infection prevention among under-five children in Ethiopia.

Prediction of incomplete immunization among under-five children in East Africa from recent demographic and health surveys: a machine learning approach.

The World Health Organization as part of the goal of universal vaccination coverage by 2030 for all individuals. The global under-five mortality rate declined from 59% in 1990 to 38% in 2019, due to high immunization coverage. Despite the significant improvements in immunization coverage, about 20 million children were either unvaccinated or had incomplete immunization, making them more susceptible to mortality and morbidity. This study aimed to identify predictors of incomplete vaccination among children under-5 years in East Africa. An analysis of secondary data from six east African countries using Demographic and Health Survey dataset from 2016 to the recent 2021 was performed. A total weighted sample of 27,806 children aged (12-35) months was included in this study. Data were extracted using STATA version 17 statistical software and imported to a Jupyter notebook for further analysis. A supervised machine learning algorithm was implemented using different classification models. All analysis and calculations were performed using Python 3 programming language in Jupyter Notebook using imblearn, sklearn, XGBoost, and shap packages. XGBoost classifier demonstrated the best performance with accuracy (79.01%), recall (89.88%), F1-score (81.10%), precision (73.89%), and AUC 86%. Predictors of incomplete immunization are identified using XGBoost models with help of Shapely additive eXplanation. This study revealed that the number of living children during birth, antenatal care follow-up, maternal age, place of delivery, birth order, preceding birth interval and mothers' occupation were the top predicting factors of incomplete immunization. Thus, family planning programs should prioritize the number of living children during birth and the preceding birth interval by enhancing maternal education. In conclusion promoting institutional delivery and increasing the number of antenatal care follow-ups by more than fourfold is encouraged.

Determinants of normal haemoglobin concentration among under-five children in Sub-Saharan Africa: a Positive deviance inquiry using cross-sectional study design.

BACKGROUND: Low haemoglobin level in children is linked with short-term and long-term consequences including developmental delay. Globally, over half of the children under the age of five years had low haemoglobin concentration. However, there is limited research on the prevalence and determinants of normal haemoglobin concentration among under-five children in sub-Saharan Africa. OBJECTIVE: To assess determinants of normal haemoglobin concentration among under-five children in SSA. DESIGN: Cross-sectional study design using a positive deviance approach SETTING: 33 SSA countries. PARTICIPANTS: 129 408 children aged 6-59 months PRIMARY AND SECONDARY OUTCOME MEASURES: A multilevel Poisson regression model with robust variance was fitted to identify determinants of normal haemoglobin concentration. An adjusted prevalence ratio with a 95% CI was reported to declare the statistical significance. RESULT: The pooled prevalence of normal haemoglobin concentration among under-five children in SSA was 34.9% (95% CI: 34.6% to 35.1%). High maternal education, middle and rich household wealth, female child, frequent antenatal care visits, non-anaemic mothers, taking anthelmintic drugs and normal nutritional status were associated with increased odds of normal haemoglobin concentration. On the other hand, higher birth order, having fever and diarrhoea, rural residence were associated with lower odds of normal haemoglobin levels. CONCLUSION: According to our finding, only four out of 10 under-five children in SSA had a normal haemoglobin level. This finding proved that anaemia among children in SSA remains a serious public health concern. Therefore, improving maternal education, provision of drugs for an intestinal parasite and early detection and treatment of maternal anaemia, febrile illness and diarrhoeal disease is important.

Trend, geographical distribution, and determinants of modern contraceptive use among married reproductive-age women, based on the 2000, 2005, 2011, and 2016 Ethiopian demographic and health survey.

BACKGROUND: The most common family planning method is modern contraception. It is a cost-effective way to reduce maternal and neonatal morbidity and mortality and enable women to make informed choices about their reproductive and sexual health. The trend of modern contraceptive utilization has shown drastic change in Ethiopia, and identifying the major factors contributing to such a drastic change is vital to improving plans and strategies for family planning programs. Therefore, this study analyzed the trend, geographical distribution, and determinants of modern contraceptive use among married reproductive-age women in Ethiopia. METHOD: This study used secondary data from the EDHS 2000-2016, collected from a population-based cross-sectional study by the Central Statistical Agency, focusing on married reproductive-age women aged 15-49. The study analyzed the modern contraceptive use trends through descriptive analyses conducted in three phases: 2000-2005, 2005-2011, and 2011-2016. The study utilized bivariable and multivariable logistic regression analyses to identify determinant factors, with significant variables declared using a P-value of 0.05 and an adjusted OR with 95% confidence interval. Analysis was conducted using STATA.14 and R. Spatial analysis was done using ArcGIS version 10.8 and SatScan™ version 9.6. RESULT: A weighted total of 33,478 women are included in the study, with a mean age of 31.4 years (8.6 SD). There was a significant increase in the trend of modern contraceptive use among married women over the study period, from 2000 to 2016, from 7.2% to 2000 to 15.7% in 2005, to 30% in 2011, and to 39.5% in 2016. The maximum increase was seen in the second phase (2005-2011), with a 14.3% increase. Factors like age of respondents, educational status, religion, residence, region, wealth index, number of living children, husbands' desire to have more children, and media exposure were found to be predictors for modern contraceptive utilization. CONCLUSION: The prevalence of modern contraceptive use is below 50%, and there is also evidence of wide geographical variation in modern contraceptive use in Ethiopia. Thus, policymakers, high institutions, and other stakeholders must work collaboratively with the government in order to improve awareness about modern contraceptive use.