Childhood obesity risk prediction with machine learning: a panel study on Korean children in Scientific Reports

Childhood obesity is a growing concern worldwide, with predictions suggesting that by 2025, half of all children could be obese. In Korea, a quarter of children and adolescents under the age of 18 are reported to be overweight or obese. To combat this issue, scientists have created a prediction model using a machine learning method to identify relevant risk factors in Korean children. The model is based on ten factors related to children and their mothers, including eating habits, activity levels, education level, self-esteem, and body mass index. The study found that, in addition to body mass index, less physical activity among children and higher self-esteem among mothers were significant risk factors for childhood obesity. The development of effective screening strategies is crucial to identify children at risk for obesity, along with their mothers. The study highlights the importance of early interventions promoting good nutrition, physical activity, and lifestyle modification to combat the obesogenic environment that many children face. Maternal psychological status was also found to be an important factor in childhood obesity, with depressed or emotionally unavailable mothers affecting the mental health of their children. This study emphasizes the need for better decision-making tools to combat childhood obesity and improve the overall health of future generations.