Efficacy of deep learning methods for predicting under-five mortality in 34 low-income and middle-income countries
Efficacy of deep learning methods for predicting under-five mortality in 34 low-income and middle-income countries
复制标题
DOI：
10.1136/bmjopen-2019-034524
复制
发表时间：
2020-01-01
期刊：
影响因子：
2.9
通讯作者：
Sun, Jing
中科院分区：
文献类型：
--
作者：
Adegbosin, Adeyinka Emmanuel;Stantic, Bela;Sun, Jing
目的探讨机器学习（ML）技术在预测低收入和中等收入国家（LMICs）5岁以下儿童死亡率（U 5 M）方面的有效性，并确定U 5 M的重要预测因素。设计这是一项横断面的概念验证研究。我们分析了人口与健康调查的数据。这些数据来自34个低收入国家，包括来自956995个独特家庭的1520018名儿童。主要和次要结局指标主要结局指标是U 5 M;次要结局是比较深度学习算法的有效性：深度神经网络（DNN）;卷积神经网络（CNN）;混合CNN-DNN与逻辑回归（LR）预测儿童生存率。结果母乳喂养时间、产前检查次数、家庭财富指数、产后护理和母亲受教育程度是5岁以下儿童的重要预测因素。我们发现，深度学习技术在儿童生存分类方面上级LR：LR灵敏度=0.47，特异性=0.53; DNN灵敏度=0.69，特异性=0.83; CNN灵敏度=0.68，特异性=0.83; CNN-DNN灵敏度=0.71，特异性=0.83。结论我们的研究结果提供了一个了解的决定因素U 5 M在LMIC。它还表明，深度学习模型比传统的分析方法更有效。
Objectives To explore the efficacy of machine learning (ML) techniques in predicting under-five mortality (U5M) in low-income and middle-income countries (LMICs) and to identify significant predictors of U5M. Design This is a cross-sectional, proof-of-concept study. Settings and participants We analysed data from the Demographic and Health Survey. The data were drawn from 34 LMICs, comprising a total of n=1 520 018 children drawn from 956 995 unique households. Primary and secondary outcome measures The primary outcome measure was U5M; secondary outcome was comparing the efficacy of deep learning algorithms: deep neural network (DNN); convolution neural network (CNN); hybrid CNN-DNN with logistic regression (LR) for the prediction of child's survival. Results We found that duration of breast feeding, number of antenatal visits, household wealth index, postnatal care and the level of maternal education are some of the most important predictors of U5M. We found that deep learning techniques are superior to LR for the classification of child survival: LR sensitivity=0.47, specificity=0.53; DNN sensitivity=0.69, specificity=0.83; CNN sensitivity=0.68, specificity=0.83; CNN-DNN sensitivity=0.71, specificity=0.83. Conclusion Our findings provide an understanding of determinants of U5M in LMICs. It also demonstrates that deep learning models are more efficacious than traditional analytical approach.