A Prediction Model for Childhood Obesity Risk Using the Machine Learning Method: A Panel Study on Korean Children

Abstract

Young children are increasingly exposed to an obesogenic environment through increased intake of processed food and decreased physical activity. Mothers’ perceptions of obesity and parenting styles also influence children’s abilities to maintain a healthy weight. This study aimed to develop a prediction model for childhood obesity in 10-year-olds and to identify relevant risk factors using a machine learning method. Data on 1185 children and their mothers were obtained from the Korean national panel study. A prediction model for obesity was developed based on factors of both children (gender, eating habits, activity, and previous body mass index) and their mothers (education level, self-esteem, and body mass index). These factors were selected based on the least absolute shrinkage and selection operator. The prediction model was validated with the Area Under the Receiver Operator Characteristic Curve of 0.82 and an accuracy of 76%. Besides body mass index for both children and mothers, significant risk factors for childhood obesity were less physical activity among children and higher self-esteem among mothers. This study adds new evidence demonstrating maternal self-esteem is related to children’s body mass index. Future studies are needed to develop effective strategies for screening young children at risk for obesity, along with their mothers.

Knowledge framework of intravenous immunoglobulin resistance in the field of Kawasaki disease: A bibliometric analysis (1997−2023)

“…ML can handle nonlinear input variables and therefore sometimes outperforms traditional models 51,52 . Currently, ML is used in clinical diagnosis and outcome prediction in many medical fields 53–55 . The diagnostic criteria for IVIG resistance in KD are based on clinical parameters, and while traditional predictive models can incorporate only a small number of clinical features, models computed by ML can integrate all aspects of clinical indicators, including continuous variables, without the need for categorization.…”

“…51,52 Currently, ML is used in clinical diagnosis and outcome prediction in many medical fields. [53][54][55] The diagnostic criteria for IVIG resistance in KD are based on clinical parameters, and while traditional predictive models can incorporate only a small number of clinical features, models computed by ML can integrate all aspects of clinical indicators, including continuous variables, without the need for categorization. Additionally, ML models can encompass a wider array of predictors, such as genetic expression, enhancing their predictive capacity.…”