Predicting South Korean adolescents vulnerable to obesity after the COVID-19 pandemic using categorical boosting and shapley additive explanation values: A population-based cross-sectional survey

Abstract

ObjectiveThis study identified factors related to adolescent obesity during the COVID-19 pandemic by using machine learning techniques and developed a model for predicting high-risk obesity groups among South Korean adolescents based on the result.Materials and methodsThis study analyzed 50,858 subjects (male: 26,535 subjects, and female: 24,323 subjects) between 12 and 18 years old. Outcome variables were classified into two classes (normal or obesity) based on body mass index (BMI). The explanatory variables included demographic factors, mental health factors, life habit factors, exercise factors, and academic factors. This study developed a model for predicting adolescent obesity by using multiple logistic regressions that corrected all confounding factors to understand the relationship between predictors for South Korean adolescent obesity by inputting the seven variables with the highest Shapley values found in categorical boosting (CatBoost).ResultsIn this study, the top seven variables with a high impact on model output (based on SHAP values in CatBoost) were gender, mean sitting hours per day, the number of days of conducting strength training in the past seven days, academic performance, the number of days of drinking soda in the past seven days, the number of days of conducting the moderate-intensity physical activity for 60 min or more per day in the past seven days, and subjective stress perception level.ConclusionTo prevent obesity in adolescents, it is required to detect adolescents vulnerable to obesity early and conduct monitoring continuously to manage their physical health.

Effect of the COVID-19 pandemic on obesity and its risk factors: a systematic review

“…Quality was assessed using the modified Newcastle–Ottawa Scale [ 19 ]. Out of included forty studies, 16 were classified as good quality [ 26 , 27 , 33 – 38 , 45 , 46 , 48 , 49 , 54 , 58 , 59 ] while twenty-four were also classified as satisfied [ 21 – 25 , 28 – 31 , 39 – 44 , 47 , 50 – 53 , 55 – 57 , 60 ]. Twenty-four articles were done on the adult population [ 22 , 23 , 25 , 26 , 28 – 30 , 36 , 38 , 42 – 44 , 46 , 48 – 50 , 55 , 57 – 59 ], five articles were done only adolescents [ 31 , 39 , 41 , 47 , 60 ], three research articles were also done on children [ 34 , 53 , 54 ], and finally, eight articles were done on both children and adolescents [ 21 , 24 , 27 , 33 , 37 , 45 , 52 , 56 ] as shown in Table 1 .…”

“…All the included studies revealed body weight changes during the pandemic. The mean weight gain during COVID-19 pandemic ranged from 0.04 (SD = 1.18) [ 42 ] to 2.8 (SD = 3.7) [ 37 ] and the prevalence of weight gain ranged from 17.9% [ 47 ] to 52.2% [ 42 ]. Despite this, some studies reported that the determinants of weight gain decreased during the COVID-19 lockdown [ 28 , 29 , 44 , 46 , 49 ].…”

“…Sedentary behaviour increases the risk of all-cause mortality. Six studies that assessed the increasing impact of sedentary time on weight gain during the COVID-19 pandemic [ 21 , 25 , 26 , 28 , 29 , 37 ], reduced sleep hours [ 20 , 27 , 52 , 54 ], increased Internet addiction during and after the pandemic [ 54 ], experienced barriers to weight management [ 57 ], length of confinement a day [ 40 , 42 , 60 ], long sitting hours [ 31 , 47 , 49 , 51 ], tobacco use [ 59 ], unnecessary alcohol conception [ 22 , 43 ], and long screen time use [ 27 – 29 , 31 , 41 , 48 ] were reported as risk factors for high BMI. Another study reported female spend more time on social media [ 55 ].…”

“…Unhealthy eating was defined as eating food that contained more calories than used, saturated fats, and food with high added sugar. Four studies identified increased consumption of sweet beverages and snacks [ 22 , 39 , 43 , 50 ], consumption of excess salt [ 22 ], eating unhealthy foods [ 25 , 36 , 38 , 43 , 46 , 50 , 57 ], drinking soda [ 47 ], overeating food [ 30 , 42 , 46 , 56 , 57 ], feeling hungry [ 39 ], and eating more recesses [ 60 ]. On the other hand, household food insecurity [ 53 , 59 ] and drinking less water during COVID-19 [ 25 ] were found to be significantly associated with obesity and weight gain.…”

“…Stress affects the human brain and activates brain hormones, such as cortisol, which increase hunger and eat more foods, leading to increased body weight. In the included studies, one was for fear of COVID-19 [ 42 ], one for anxiety [ 42 ], five for increased stress [ 20 , 38 , 44 , 47 , 48 ], one for poor mood development [ 50 ], and four studies [ 20 , 38 , 42 , 44 , 47 , 48 , 50 ] reported a statistically significant association with depression [ 20 , 26 , 48 ]. As shown Table 1 .…”