Predicting Childhood Obesity Based on Single and Multiple Well-Child Visit Data Using Machine Learning Classifiers

Abstract

Childhood obesity is a public health concern in the United States. Consequences of childhood obesity include metabolic disease and heart, lung, kidney, and other health-related comorbidities. Therefore, the early determination of obesity risk is needed and predicting the trend of a child’s body mass index (BMI) at an early age is crucial. Early identification of obesity can lead to early prevention. Multiple methods have been tested and evaluated to assess obesity trends in children. Available growth charts help determine a child’s current obesity level but do not predict future obesity risk. The present methods of predicting obesity include regression analysis and machine learning-based classifications and risk factor (threshold)-based categorizations based on specific criteria. All the present techniques, especially current machine learning-based methods, require longitudinal data and information on a large number of variables related to a child’s growth (e.g., socioeconomic, family-related factors) in order to predict future obesity-risk. In this paper, we propose three different techniques for three different scenarios to predict childhood obesity based on machine learning approaches and apply them to real data. Our proposed methods predict obesity for children at five years of age using the following three data sets: (1) a single well-child visit, (2) multiple well-child visits under the age of two, and (3) multiple random well-child visits under the age of five. Our models are especially important for situations where only the current patient information is available rather than having multiple data points from regular spaced well-child visits. Our models predict obesity using basic information such as birth BMI, gestational age, BMI measures from well-child visits, and gender. Our models can predict a child’s obesity category (normal, overweight, or obese) at five years of age with an accuracy of 89%, 77%, and 89%, for the three application scenarios, respectively. Therefore, our proposed models can assist healthcare professionals by acting as a decision support tool to aid in predicting childhood obesity early in order to reduce obesity-related complications, and in turn, improve healthcare.

Estimation of Obesity Levels through the Proposed Predictive Approach Based on Physical Activity and Nutritional Habits

“…Compared with those of the RF and XGBoost algorithms, the LR model exhibited superior predictions, fortified by optimal hyperparameters and feature selection. Notably, the LR model’s classification results surpassed those of the models employed in other analogous studies [ 44 , 45 , 46 ]. These findings underscore the LR model’s efficacy in the context of obesity classification and prediction.…”

“…The methods used different data sets depending on the available information: (1) one well-child visit, (2) several well-child visits before age two, and (3) several random well-child visits before age five. The models could classify a child’s obesity status (normal, overweight, or obese) at age five with 89%, 77%, and 89% accuracy, respectively [ 45 ]. Another study used AI and machine learning to analyze a dataset of EHRs with data on people’s health and lifestyle.…”

Elementos básicos de Análisis Inteligente de Datos

“…Estos modelos predicen la obesidad utilizando información básica como el IMC al nacer, la edad gestacional, las medidas del IMC de las visitas de niño sano y el sexo. Los modelos pueden predecir la categoría de obesidad de un niño (normal, con sobrepeso u obeso) a los cinco años de edad con una precisión del 89 %, 77 % y 89% (Mondal et al, 2023).…”

DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework

“…These data are essential to develop accurate algorithms to predict obesity rates and provide personalized feedback to individuals. The availability of such datasets can enable researchers and healthcare providers to develop more effective interventions and prevention strategies for childhood and adolescent obesity [11], [35], [36]. However, there are various challenges in collecting and analyzing these data, such as ensuring data quality, protecting privacy, and addressing ethical considerations [29], [37], [38].…”

“…On average, they achieved an area-under-the-curve score of 0.88. Mondal et al [35] employed a machine learning (ML) classifier to categorize individuals into three groups based on childhood health maintenance data: normal weight, overweight, and obese. The experimental results demonstrated the classification accuracies of 89%, 77%, and 89% for the three respective scenarios.…”