Sánchez-Martínez Luis Javier, Charle-Cuéllar Pilar, Gado Abdoul Aziz, Ousmane Nassirou, Hernández Candela Lucía, López-Ejeda Noemí
Unit of Physical Anthropology, Department of Biodiversity, Ecology and Evolution, Faculty of Biological Sciences, Complutense University of Madrid, 28040 Madrid, Spain.
Action Against Hunger, 28002 Madrid, Spain.
Nutrients. 2024 Dec 6;16(23):4213. doi: 10.3390/nu16234213.
BACKGROUND/OBJECTIVES: Child acute malnutrition is a global public health problem, affecting 45 million children under 5 years of age. The World Health Organization recommends monitoring weight gain weekly as an indicator of the correct treatment. However, simplified protocols that do not record the weight and base diagnosis and follow-up in arm circumference at discharge are being tested in emergency settings. The present study aims to use machine learning techniques to predict weight gain based on the socio-economic characteristics at admission for the children treated under a simplified protocol in the Diffa region of Niger.
The sample consists of 535 children aged 6-59 months receiving outpatient treatment for acute malnutrition, for whom information on 51 socio-economic variables was collected. First, the Variable Selection Using Random Forest (VSURF) algorithm was used to select the variables associated with weight gain. Subsequently, the dataset was partitioned into training/testing, and an ensemble model was adjusted using five algorithms for prediction, which were combined using a Random Forest meta-algorithm. Afterward, Receiver Operating Characteristic (ROC) curves were used to identify the optimal cut-off point for predicting the group of individuals most vulnerable to developing low weight gain.
The critical variables that influence weight gain are water, hygiene and sanitation, the caregiver's employment-socio-economic level and access to treatment. The final ensemble prediction model achieved a better fit (R = 0.55) with respect to the individual algorithms (R = 0.14-0.27). An optimal cut-off point was identified to establish low weight gain, with an Area Under the Curve (AUC) of 0.777 at a value of <6.5 g/kg/day. The ensemble model achieved a success rate of 84% (78/93) at the identification of individuals below <6.5 g/kg/day in the test set.
The results highlight the importance of adapting the cut-off points for weight gain to each context, as well as the practical usefulness that these techniques can have in optimizing and adapting to the treatment in humanitarian settings.
背景/目的：儿童急性营养不良是一个全球性公共卫生问题，影响着4500万5岁以下儿童。世界卫生组织建议每周监测体重增加情况，作为正确治疗的指标。然而，在紧急情况下，正在测试一些简化方案，这些方案在出院时不记录体重，而是以臂围为基础进行诊断和随访。本研究旨在使用机器学习技术，根据在尼日尔迪法地区接受简化方案治疗的儿童入院时的社会经济特征，预测体重增加情况。
样本包括535名6至59个月大接受急性营养不良门诊治疗的儿童，收集了关于51个社会经济变量的信息。首先，使用随机森林变量选择（VSURF）算法选择与体重增加相关的变量。随后，将数据集划分为训练/测试集，并使用五种算法调整集成模型进行预测，这些算法通过随机森林元算法进行组合。之后，使用受试者工作特征（ROC）曲线确定预测最易出现低体重增加人群组的最佳切点。
影响体重增加的关键变量是水、卫生和环境卫生、照顾者的就业-社会经济水平以及获得治疗的机会。最终的集成预测模型相对于单个算法（R = 0.14 - 0.27）实现了更好的拟合（R = 0.55）。确定了一个用于判定低体重增加的最佳切点，当值<6.5 g/kg/天时，曲线下面积（AUC）为0.777。集成模型在测试集中识别<6.5 g/kg/天的个体时成功率达到84%（78/93）。
结果强调了根据具体情况调整体重增加切点的重要性，以及这些技术在优化和适应人道主义环境中的治疗方面的实际用途。
