Department of Statistics, College of Natural and Computational Sciences, Dire Dawa University, Dire Dawa, Ethiopia.
BMC Med Inform Decis Mak. 2022 Sep 5;22(1):232. doi: 10.1186/s12911-022-01981-9.
Birth weight is a significant determinant of the likelihood of survival of an infant. Babies born at low birth weight are 25 times more likely to die than at normal birth weight. Low birth weight (LBW) affects one out of every seven newborns, accounting for about 14.6 percent of the babies born worldwide. Moreover, the prevalence of LBW varies substantially by region, with 7.2 per cent in the developed regions and 13.7 per cent in Africa, respectively. Ethiopia has a large burden of LBW, around half of Africa. These newborns were more likely to die within the first month of birth or to have long-term implications. These are stunted growth, low IQ, overweight or obesity, developing heart disease, diabetes, and early death. Therefore, the ability to predict the LBW is the better preventive measure and indicator of infant health risks.
This study implemented predictive LBW models based on the data obtained from the Ethiopia Demographic and Health Survey 2016. This study was employed to compare and identify the best-suited classifier for predictive classification among Logistic Regression, Decision Tree, Naive Bayes, K-Nearest Neighbor, Random Forest (RF), Support Vector Machine, Gradient Boosting, and Extreme Gradient Boosting.
Data preprocessing is conducted, including data cleaning. The Normal and LBW are the binary target category in this study. The study reveals that RF was the best classifier and predicts LBW with 91.60 percent accuracy, 91.60 percent Recall, 96.80 percent ROC-AUC, 91.60 percent F1 Score, 1.05 percent Hamming loss, and 81.86 percent Jaccard score.
The RF predicted the occurrence of LBW more accurately and effectively than other classifiers in Ethiopia Demographic Health Survey. Gender of the child, marriage to birth interval, mother's occupation and mother's age were Ethiopia's top four critical predictors of low birth weight in Ethiopia.
出生体重是婴儿存活可能性的重要决定因素。出生体重低的婴儿死亡的可能性是正常出生体重婴儿的 25 倍。低出生体重（LBW）影响全球每七个新生儿中的一个，占全球出生婴儿的 14.6%。此外，LBW 的患病率在区域之间存在显著差异，发达地区为 7.2%，非洲为 13.7%。埃塞俄比亚的 LBW 负担很大，约占非洲的一半。这些新生儿在出生后的第一个月内更有可能死亡，或有长期影响。这些影响包括生长迟缓、低智商、超重或肥胖、心脏病、糖尿病和早逝。因此，预测 LBW 的能力是更好的预防措施和婴儿健康风险的指标。
本研究基于 2016 年埃塞俄比亚人口与健康调查获得的数据，建立了预测 LBW 的模型。本研究旨在比较和确定最适合预测分类的分类器，包括逻辑回归、决策树、朴素贝叶斯、K-最近邻、随机森林（RF）、支持向量机、梯度提升和极端梯度提升。
进行了数据预处理，包括数据清洗。本研究的正常和 LBW 是二进制目标类别。研究表明，RF 是最好的分类器，预测 LBW 的准确率为 91.60%，召回率为 91.60%，ROC-AUC 为 96.80%，F1 得分为 91.60%，汉明损失为 1.05%，杰卡德得分 81.86%。
在埃塞俄比亚人口健康调查中，RF 比其他分类器更准确和有效地预测了 LBW 的发生。在埃塞俄比亚，儿童的性别、婚姻到出生的间隔时间、母亲的职业和母亲的年龄是低出生体重的前四个关键预测因素。
