[论文解读] Predicting Anemia Among Under-Five Children in Nepal Using Machine Learning and Deep Learning
本研究基准对10种机器学习/深度学习模型,使用NDHS 2022数据及13个社会人口特征预测尼泊尔6-59月儿童贫血,采用SMOTE处理类别不平衡。
Childhood anemia remains a major public health challenge in Nepal and is associated with impaired growth, cognition, and increased morbidity. Using World Health Organization hemoglobin thresholds, we defined anemia status for children aged 6-59 months and formulated a binary classification task by grouping all anemia severities as \emph{anemic} versus \emph{not anemic}. We analyzed Nepal Demographic and Health Survey (NDHS 2022) microdata comprising 1,855 children and initially considered 48 candidate features spanning demographic, socioeconomic, maternal, and child health characteristics. To obtain a stable and substantiated feature set, we applied four features selection techniques (Chi-square, mutual information, point-biserial correlation, and Boruta) and prioritized features supported by multi-method consensus. Five features: child age, recent fever, household size, maternal anemia, and parasite deworming were consistently selected by all methods, while amenorrhea, ethnicity indicators, and provinces were frequently retained. We then compared eight traditional machine learning classifiers (LR, KNN, DT, RF, XGBoost, SVM, NB, LDA) with two deep learning models (DNN and TabNet) using standard evaluation metrics, emphasizing F1-score and recall due to class imbalance. Among all models, logistic regression attained the best recall (0.701) and the highest F1-score (0.649), while DNN achieved the highest accuracy (0.709), and SVM yielded the strongest discrimination with the highest AUC (0.736). Overall, the results indicate that both machine learning and deep learning models can provide competitive anemia prediction and the interpretable features such as child age, infection proxy, maternal anemia, and deworming history are central for risk stratification and public health screening in Nepal.
研究动机与目标
- 评估是否可以使用NDHS 2022数据中6-59个月儿童的社会人口特征来预测贫血状态(任一严重程度)。
- 通过应用多种特征选择技术并在方法之间达成共识来识别鲁棒的特征子集。
- 在存在类别不平衡的情况下,使用合适的指标评估模型性能,并确定在资源有限环境中的实际筛查潜力。
- 在可解释性模型(如逻辑回归)与神经网络方法在此情境中的相对优劣进行比较。
提出的方法
- 通过移除目标变量缺失和高缺失变量的NDHS 2022数据来预处理;填补其余缺口。
- 将特征转换为分类表示,并应用80/20的训练-测试拆分,采用分层抽样。
- 使用四种特征选择方法(Chi-square、Mutual Information、Point-Biserial、Boruta),并选取得到多方法共识支持的特征。
- 用SMOTE平衡训练数据并纳入建模流程,以避免数据泄露。
- 使用重复分层交叉验证与网格搜索训练并优化十个模型(LR、KNN、DT、RF、XGBoost、SVM、NB、LDA、DNN、TabNet)。
- 用准确率、精确率、召回率、F1分数、平均精度、AUC,以及Cohen’s kappa评估模型;由于类别不平衡,强调召回率和F1。

实验结果
研究问题
- RQ1ML/DL模型是否可以使用NDHS 2022中的社会人口特征预测尼泊尔儿童贫血状态?
- RQ2在多种特征选择方法中,哪些特征对贫血风险的信息量最为一致?
- RQ3在SMOTE平衡训练的情况下,不同ML/DL算法在此场景中的表现如何?
- RQ4逻辑回归在这一表格型、小样本、高度不平衡的问题上是否仍具备与神经网络竞争力?
- RQ5模型表现对于在尼泊尔的无创筛查与公共卫生筛查计划有何意义?
主要发现
- 逻辑回归在召回率(70.1%)和F1分数(64.9%)上表现最佳,显示出识别贫血病例的强大能力。
- SVM提供最高的AUC(0.736),在贫血与非贫血儿童之间具有较强的区分度。
- DNN实现最高的准确率(70.9%)和精确率(66.4%),但召回率(60.4%)低于LR。
- 总体来说,各指标的模型性能处在60-70%区间,反映出社会人口代理变量对直接临床指标的预测能力有限。
- 最具预测力的特征包括儿童年龄、发热、家庭规模、母亲贫血,以及寄生虫驱虫等因素,若干民族和省份指标也具信息量。
- 模型普遍受益于SMOTE来解决类别不平衡,交叉验证提示具有较强的泛化能力。

更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。