Prediction of Nutritional Requirements for Children’s Growth and Adolescents using Machine Learning

In many countries, malnutrition and stunting in children and adolescents are on the rise. They pose a substantial threat to current and near-future health care systems since they are associated with a number of comorbidities. Predictive models for children's and adolescent nutritional needs and outcomes are essential to better understanding its origins and creating suitable prevention approaches. Machine learning models are becoming increasingly useful in this field because of their predictive strength, their ability to model complex, nonlinear interactions between variables, and their capacity to handle high-dimensional data. For non-binary classification problems, the Decision Tree 4.5 machine learning algorithm is a good fit. Decision Tree 4.5 has advantages over similar systems when it comes to handling data in a range of formats. This study examined the nutritional needs of primary school-aged children. Using a decision tree, 7 until 12-year-old elementary school students were tested with a total population of 360 students, and the results showed that 79% of them had normal weight, 12.5% were underweight, and 7.8% were overweight.