Qasrawi Radwan, Abu Al-Halawa Diala
Department of Computer Science, Al-Quds University, Jerusalem, Palestine.
Department of Computer Engineering, Istinye University, Istanbul, Turkey.
Front Nutr. 2022 May 10;9:838937. doi: 10.3389/fnut.2022.838937. eCollection 2022.
Nutritional inadequacy has been a major health problem worldwide. One of the many health problems that result from it is anemia. Anemia is considered a health concern among all ages, particularly children, as it has been associated with cognitive and developmental delays. Researchers have investigated the association between nutritional deficiencies and anemia through various methods. As novel analytical methods are needed to ascertain the association and reveal indirect ones, we aimed to classify nutritional anemia using the cluster analysis approach. In this study, we included 4,762 students aged between 10 and 17 years attending public and UNRWA schools in the West Bank. Students' 24-h food recall and blood sample data were collected for nutrient intake and hemoglobin analysis. The K-means cluster analysis was used to cluster the hemoglobin levels into two groups. Vitamin B12, folate, and iron intakes were used as the indicators of nutrient intake associated with anemia and were classified as per the Recommended Dietary Allowance (RDA) values. We applied the Classification and Regression Tree (CRT) model for studying the association between hemoglobin clusters and vitamin B12, folate, and iron intakes, sociodemographic variables, and health-related risk factors, accounting for grade and age. Results indicated that 46.4% of the students were classified into the low hemoglobin cluster, and 60.7, 72.5, and 30.3% of vitamin B12, folate, and iron intakes, respectively, were below RDA. The CRT analysis indicated that vitamin B12, iron, and folate intakes are important factors related to anemia in girls associated with age, locality, food consumption patterns, and physical activity levels, while iron and folate intakes were significant factors related to anemia in boys associated with the place of residence and the educational level of their mothers. The deployment of clustering and classification techniques for identifying the association between anemia and nutritional factors might facilitate the development of nutritional anemia prevention and intervention programs that will improve the health and wellbeing of schoolchildren.
营养不足一直是全球范围内的一个主要健康问题。由此导致的众多健康问题之一是贫血。贫血被认为是所有年龄段人群，尤其是儿童的一个健康问题，因为它与认知和发育迟缓有关。研究人员通过各种方法调查了营养缺乏与贫血之间的关联。由于需要新的分析方法来确定这种关联并揭示间接关联，我们旨在使用聚类分析方法对营养性贫血进行分类。在本研究中，我们纳入了约旦河西岸公立学校和近东救济工程处学校的4762名10至17岁的学生。收集了学生的24小时食物回忆和血液样本数据，用于营养摄入和血红蛋白分析。使用K均值聚类分析将血红蛋白水平分为两组。维生素B12、叶酸和铁的摄入量被用作与贫血相关的营养摄入指标，并根据推荐膳食摄入量（RDA）值进行分类。我们应用分类与回归树（CRT）模型来研究血红蛋白聚类与维生素B12、叶酸和铁的摄入量、社会人口统计学变量以及与健康相关的风险因素之间的关联，并考虑了年级和年龄因素。结果表明，46.4%的学生被归类为低血红蛋白组，维生素B12、叶酸和铁摄入量分别有60.7%、72.5%和30.3%低于RDA。CRT分析表明，维生素B12（钴胺素）、铁和叶酸的摄入量是与年龄、地区、食物消费模式和身体活动水平相关的女孩贫血的重要因素，而铁和叶酸的摄入量是与居住地和母亲教育水平相关的男孩贫血的重要因素。采用聚类和分类技术来确定贫血与营养因素之间的关联，可能有助于制定营养性贫血预防和干预计划，从而改善学童的健康和福祉。
