Prediction model study of overweight and obesity in preschool children with allergic diseases from an ecological perspective

Abstract

Background Allergic diseases have a high incidence in childhood and a high chance to be carried over into adulthood unless appropriately treated during childhood, it is important that healthcare providers actively manage these diseases. This study was to identify multidimensional factors that affect weight gain in preschool children with allergic diseases. Methods The overweight and obesity prediction model for children with allergic diseases was analyzed using multiple logistic regression analysis and a decision tree model and the present study was a secondary data analysis study that used data from the Panel Study on Korean Children conducted by the Korea Institute of Child Care and Education. Results The significance of this study is identify multidimensional factors that affect weight gain in preschool children with allergic diseases, which found that children (gender, sitting time during weekdays, sleeping hours during weekends,), parent (education level, mother’s job, quality of the home environment), local community (convenience of local community facilities, satisfaction level with local community facilities, quality of childcare in the local community) characteristics affected overweight and obesity at multidimensional levels as risk factors. Conclusions The significance of this study is identify multidimensional factors that affect weight gain in preschool children with allergic diseases using the data of the Panel Study on Korean Children, which found that children, parent, local community characteristics affected overweight and obesity at multidimensional levels as risk factors.

Health Information Prediction System of Infant Sports Based on Deep Learning Network

“…Han and Kim [ 18 ] proposed a new overweight and obesity prediction model for children in healthcare centers. A logistic regression algorithm is used to analyze health-related information in the data analysis process.…”

“…Therefore, the detection accuracy is stabilized for the training process (refer to Figure 6 ). In the comparative analysis, the methods TL-CAR [ 26 ], MLRA+DT [ 18 ], and AICF [ 28 ] are considered for validating accuracy, precision, error, and time complexity.…”