Predicting Factors Affecting Adolescent Obesity Using General Bayesian Network and What-If Analysis

Abstract

With the remarkable improvement in people’s socioeconomic living standards around the world, adolescent obesity has increasingly become an important public health issue that cannot be ignored. Thus, we have implemented its use in an attempt to explore the viability of scenario-based simulations through the use of a data mining approach. In doing so, we wanted to explore the merits of using a General Bayesian Network (GBN) with What-If analysis while exploring how it can be utilized in other areas of public health. We analyzed data from the 2017 Korean Youth Health Behavior Survey conducted directly by the Korea Centers for Disease Control & Prevention, including 19 attributes and 11,206 individual data points. Our simulations found that by manipulating the amount of pocket money-between $60 and $80-coupled with a low-income background, it has a high potential to increase obesity compared with other simulated factors. Additionally, when we manipulated an increase in studying time with a mediocre academic performance, it was found to potentially increase pressure on adolescents, which subsequently led to an increased obesity outcome. Lastly, we found that when we manipulated an increase in a father’s education level while manipulating a decrease in mother’s education level, this had a large effect on the potential adolescent obesity level. Although obesity was the chosen case, this paper acts more as a proof of concept in analyzing public health through GBN and What-If analysis. Therefore, it aims to guide health professionals into potentially expanding their ability to simulate certain outcomes based on predicted changes in certain factors concerning future public health issues.

Machine Learning Models to Predict Childhood and Adolescent Obesity: A Review

“…The former models use traditional statistical techniques, mainly logistic regression, [ 34 , 35 , 36 , 37 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 ] although there are cases using linear regression [ 40 ], quantile regression [ 38 ], and ordinal logistic regression. [ 47 ] The ML models use a wide variety of ML methods: ANN [ 56 , 57 , 58 , 67 , 68 , 70 , 75 ], SVM [ 58 , 66 , 67 ], DT [ 58 , 64 , 65 , 67 , 68 , 69 , 70 , 73 ], NB [ 58 , 60 , 61 , 62 , 66 , 67 ], BN [ 58 , 65 , 67 , 76 ], LASSO [ 72 , 74 ], kNN [ 70 ], RF [ 59 , 65 , 68 , 72 ], GBM [ 72 , 77 ], and DL (RNN […”

“…Works that stand out for their use of specially wide sets of multidomain predictor variables are those of Rehkopf et al [ 59 ] (diet; physical activity; and psychological, social, and parental health); Wiechman et al [ 69 ] (demographics, caregiver feeding style, feeding practices, home environment, diet, social support, spousal support, family life, etc. ); and Kim et al [ 76 ] (wealth, smartphone use, pocket money, academic performance, sleeping quality, etc.) The latter work is interesting also because it makes a “what-if” analysis where some variables are modified, and their concerted effect on the predicted obesity is evaluated; this is an interesting approach to use ML models as simulation tools to suggest possible therapeutic or preventive interventions.…”

“…A South-Korean dataset was also used in order to understand factors affecting obesity is that of Kim et al [ 76 ], although in this case it deals with adolescent obesity. They used a cohort of >11,000 students from South Korea and 19 predictor variables from questionnaires of different domains: sociological, anthropometric, smartphone use, obesity, other.…”

Identifying High-Risk Factors of Depression in Middle-Aged Persons with a Novel Sons and Spouses Bayesian Network Model

“…As depression is a mental disease, it is not as common within the population and hence presents an imbalanced dataset. Thus, following prior research, we analyzed the performance based on accuracy, precision, and the F-Measure metric [ 13 ]. However, in medical classification tasks, the F-Measure is usually considered the best predictor.…”

“…This approach involves three stages, including feature selection, a supervised Sons and Spouses Bayesian Network (SS) [ 12 ], and genetic optimization through a genetic algorithm for understanding what solutions show the greatest risk to inducing depression. Although not common within the medical field, this approach has been successfully implemented in exploring other medical fields, including adolescent obesity [ 13 ], and thus we believe this methodology is well adapted for the current issue presented in this study.…”