A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.
A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones.
复制标题
DOI：
10.1186/s12911-021-01652-1
复制
发表时间：
2021-10-24
影响因子：
3.5
通讯作者：
Muluneh EK
中科院分区：
文献类型：
--
作者：
Fenta HM;Zewotir T;Muluneh EK
营养不良是发展中国家儿童死亡的主要原因。本文旨在探讨机器学习(ML)方法在预测埃塞俄比亚行政区五岁以下儿童营养不良方面的有效性，并确定最重要的预测因素。这项研究使用了ML技术，使用了埃塞俄比亚的回溯性横断面调查数据，这是一项在2000年、2005年、2011年和2016年收集的具有全国代表性的数据。我们研究了六种常用的最大似然算法：Logistic回归、最小绝对收缩和选择算子(L-1正则化Logistic回归)、L-2正则化(岭)、弹性网络、神经网络和随机森林(RF)。使用灵敏度、特异度、准确性和曲线下面积来评估这些模型的性能。根据不同的性能评价，选择RF算法作为最优最大似然模型。按照重要性顺序，城乡居住地、父母识字率和居住地是埃塞俄比亚各行政区五岁以下儿童营养状况差异的主要决定因素。我们的结果表明，所考虑的机器学习分类算法可以有效地预测埃塞俄比亚行政区的五岁以下儿童营养不良状况。在埃塞俄比亚北部发现了持续的五岁以下儿童营养不良状况。确定这样的高风险地区可以为试图减少儿童营养不良的决策者提供有用的信息。网上版载有补充材料，可在10.1186/s12911-021-01652-1查阅。
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. 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. 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. 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. The online version contains supplementary material available at 10.1186/s12911-021-01652-1.
登录
查看更多内容
影响因子：
20.1
作者：
Ambale-Venkatesh B;Yang X;Wu CO;Liu K;Hundley WG;McClelland R;Gomes AS;Folsom AR;Shea S;Guallar E;Bluemke DA;Lima JAC
通讯作者：
Lima JAC
影响因子：
2.9
作者：
Farran B;Channanath AM;Behbehani K;Thanaraj TA
通讯作者：
Thanaraj TA
影响因子：
4.4
作者：
Behroozi M;Sami A
通讯作者：
Sami A
影响因子：
2.2
作者：
Gebre, Abel;Reddy, P. Surender;Kahssay, Molla
通讯作者：
Kahssay, Molla
影响因子：
18.2
作者：
Adler, Eric D.;Voors, Adriaan A.;Yagil, Avi
通讯作者：
Yagil, Avi