Dataset Information

A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.

ABSTRACT:

Background

Undernutrition is the main cause of child death in developing countries. This paper aimed to explore the efficacy of machine learning (ML) approaches in predicting under-five undernutrition in Ethiopian administrative zones and to identify the most important predictors.

Method

The study employed ML techniques using retrospective cross-sectional survey data from Ethiopia, a national-representative data collected in the year (2000, 2005, 2011, and 2016). We explored six commonly used ML algorithms; Logistic regression, Least Absolute Shrinkage and Selection Operator (L-1 regularization logistic regression), L-2 regularization (Ridge), Elastic net, neural network, and random forest (RF). Sensitivity, specificity, accuracy, and area under the curve were used to evaluate the performance of those models.

Results

Based on different performance evaluations, the RF algorithm was selected as the best ML model. In the order of importance; urban-rural settlement, literacy rate of parents, and place of residence were the major determinants of disparities of nutritional status for under-five children among Ethiopian administrative zones.

Conclusion

Our results showed that the considered machine learning classification algorithms can effectively predict the under-five undernutrition status in Ethiopian administrative zones. Persistent under-five undernutrition status was found in the northern part of Ethiopia. The identification of such high-risk zones could provide useful information to decision-makers trying to reduce child undernutrition.

SUBMITTER: Fenta HM

PROVIDER: S-EPMC8542294 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.

Fenta Haile Mekonnen HM Zewotir Temesgen T Muluneh Essey Kebede EK

BMC medical informatics and decision making 20211024 1

<h4>Background</h4>Undernutrition is the main cause of child death in developing countries. This paper aimed to explore the efficacy of machine learning (ML) approaches in predicting under-five undernutrition in Ethiopian administrative zones and to identify the most important predictors.<h4>Method</h4>The study employed ML techniques using retrospective cross-sectional survey data from Ethiopia, a national-representative data collected in the year (2000, 2005, 2011, and 2016). We explored six c ...[more]

PMID: 34689769

Similar Datasets

Project description:IntroductionIn Ethiopia, undernutrition is the common public health concern, swaying the lives of lots of adolescent girls. Its sequelae are not only limited to them, but rather their upcoming offspring are vulnerable too. Even though some studies have been carried out in different parts of the country, the national pooled prevalence and determinants of undernutrition are not known. Therefore, this study is aimed at determining the pooled prevalence and determinants of undernutrition among adolescent girls in Ethiopia.MethodsPublished articles will be retrieved from databases such as Medline and PubMed. Electronic search engines such as Google Scholar and Google will be used. To identify eligible studies, the Joanna Briggs Institute quality appraisal checklists prepared for different study designs will be used. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist will be used to maintain the scientific robustness of the study. The presence of heterogeneity among studies will be examined by forest plot as well as I2 heterogeneity test. Potential causes of heterogeneity will be explored by carrying out sensitivity and subgroup analyses. The DerSimonian and Laird random-effects model will be used provided that heterogeneity is observed. Publication bias will be examined by observing funnel plots, and objectively by Egger's regression test. If the funnel plot is asymmetric and/or Egger's test was found to be statistically significant (p<0.05), the trim and fill (Duval and Tweedie's) analysis will be performed. The presence of a statistical association between independent and dependent variables will be declared if the p value is <0.05 with the 95% CI.Ethics and disseminationSince this is a systematic review and meta-analysis, ethical clearance will not be a concern. The results of the study will be published in a peer-reviewed reputable journal and presented at different scientific research conferences.Trial registration numberCRD42018106180.

Project description:BackgroundUnderstanding the burden and contextual risk factors is critical for developing appropriate interventions to control undernutrition.MethodsThis study used data from the 2014 Ghana Demographic and Health Survey to estimate the prevalence of underweight, stunting, and wasting. Single multiple logistic regressions were used to identify the factors associated with underweight, wasting and stunting. The study involved 2720 children aged 0-59 months old and mother pairs. All analyses were done in STATA/IC version 15.0. Statistical significance was set at p<0.05.ResultsThe prevalence of underweight, wasting and stunting were 10.4%, 5.3%, and 18.4% respectively. The age of the child was associated with underweight, wasting and stunting, whereas the sex was associated with wasting and stunting. Normal or overweight/obese maternal body mass index category, high woman's autonomy and middle-class wealth index were associated with a lower odds of undernutrition. The factors that were associated with a higher odds of child undernutrition included: low birth weight (<2.5 kg), minimum dietary diversity score (MDDS), a higher (≥4th) birth order number of child, primary educational level of husband/partner and domicile in the northern region of Ghana.ConclusionThere is still a high burden of child undernutrition in Ghana. The age, sex, birth weight, birth order and the MDDS of the child were the immediate factors associated with child undernutrition. The intermediate factors that were associated with child undernutrition were mainly maternal related factors and included maternal nutritional status and autonomy. Distal level factors which were associated with a higher odds of child undernutrition were the wealth index of the household, paternal educational status and region of residence. We recommend that interventions and policies for undernutrition should address socioeconomic inequalities at the community level while factoring in women empowerment programmes.

Project description:BackgroundMalnutrition and human immunodeficiency virus (HIV) are interlaced in a vicious cycle and worsened in low and middle-income countries. In Ethiopia, even though individuals are dually affected by both malnutrition and HIV, there is no a nationwide study showing the proportion of malnutrition among HIV-positive adults. Consequently, this review addressed the pooled burden of undernutrition among HIV-positive adults in Ethiopia.MethodsWe searched for potentially relevant studies through manual and electronic searches. An electronic search was carried out using the database of PubMed, Google Scholar, and Google for gray literature and reference lists of previous studies. A standardized data extraction checklist was used to extract the data from each original study. STATA Version 13 statistical software was used for our analysis. Descriptive summaries were presented in tables, and the quantitative result was presented in a forest plot. Heterogeneity within the included studies was examined using the Cochrane Q test statistics and I 2 test. Finally, a random-effects meta-analysis model was computed to estimate the pooled proportion of undernutrition among HIV-positive adults.ResultsAfter reviewing 418 studies, 15 studies met the inclusion criteria and were included in the meta-analysis. Findings from 15 studies revealed that the pooled percentage of undernutrition among HIV-positive adults in Ethiopia was 26% (95% CI: 22, 30%). The highest percentage of undernutrition (46.8%) was reported from Jimma University specialized hospital, whereas the lowest proportion of undernutrition (12.3%) was reported from Dilla Hospital. The subgroup analyses of this study also indicated that the percentage of undernourishment among HIV-positive adults is slightly higher in the Northern and Central parts of Ethiopia (27.5%) as compared to the Southern parts of Ethiopia (25%).ConclusionThis study noted that undernutrition among HIV-positive adults in Ethiopia was quite common. This study also revealed that undernutrition is more common among HIV-positive adults with advanced disease stage, anemia, diarrhea, CD4 count less than 200 cells/mm3, and living in rural areas. Based on our findings, we suggested that all HIV-positive adults should be assessed for nutritional status at the time of ART commencement.

Dataset Information

A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.

Background

Method

Results

Conclusion

Publications

A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets