• Journal of the Korean Society of Food Science and Nutrition
• /
• v.38 no.6
• /
• pp.694-708
• /
• 2009

The principal objective of this study was to determine the effects of smoking & drinking on the diet, nutrient intake, and overall health. A sample of 262 youths, aged 16 to 18 year-old, was randomly selected from Seoul and its vicinity. The subjects participated by answering survey questions including general questions, questions regarding health, smoking & drinking habits, dietary habits, nutrient intake, physical characteristics, and smoking cessation plans. The average height, weight, and BMI of the subjects were $173.5{\pm}6.8\;cm$, $64.8{\pm}11.8\;kg$, and $21.4{\pm}3.7\;kg/m^2$, respectively. Among the subjects, 88% appeared to be interested in health and 43.5% of youth asserted that the best way to keep healthy was to engage in regular exercise. Among 63 smokers, 52 students (82.5%) used alcoholic beverages while 11 students (17.5%) did not use alcoholic beverages, meaning that smoking was a causative factor in drinking. 55.6% of youth reported beginning to smoke in middle school, and 38.1% of them asserted that curiosity was the motive for smoking. The youth reported that the craving for smoking was highest when hungry, and the best place to smoke was the restroom. 20 students (69.0%) answered that the only way to quit smoking was just to stop. 12 students (44.4%) reported that the main reason for failures in smoking cessation attempts was a lack of intention or willpower. 87.1% of all subjects answered that they were inclined to quit smoking, and 56.7% of them would be interested in attending a smoking cessation program if they had the opportunity. Among the smoking and drinking group, 50% of drinkers began to drink in high school, and the reason for drinking given was peer pressure-40% of drinkers answered that they wished to quit drinking. 34.4% of students appeared to have breakfast everyday, but 16.4% of students answered that they had quit eating breakfast. 52.5% of all students reported that the principal reason for overeating was the presence of one's favorite food, and the smoking and drinking group reported overeating more frequently than other groups (p<0.05). 72.6% of all subjects reported eating interim meals $1{\sim}2$ times daily, 36.4% of smokers ate carbonated beverages, 38.5% ate ice cream as a interim meal, and 38.5% of the drinking and smoking groups ate fruits, 26.9% of them ate fried foods, and some of them ate fast foods as a interim meal. Among smokers, the ratio of eating fat-rich foods, and meats such as kalbi and samgyupsal more than two times per week was higher, and 54.3% of smokers ate ice cream, cookies, and carbonated beverages more than two times per week (p<0.05). The total nutrient intake of the $15{\sim}19$-year youth group was much higher than the standard value. The energy intake of the smoking group and the drinking and smoking group was significantly higher than that of the normal group (p<0.05). Intakes of phosphorus (p<0.05), cholesterol (p<0.05), and sodium (p<0.05) were the highest among all groups. Accordingly, it is recommended that practical education programs be implemented to teach young students to resist peer pressures to smoke and drink. Additionally, education that acknowledges the importance of nutrition is necessary to avoid preferential eating and overeating due to smoking and drinking.such education can also teach students to eat a balanced diet and improve their physical development.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.41 no.2
• /
• pp.205-212
• /
• 2012

This study was performed to investigate the prevalence of metabolic syndrome (MS) and assess nutrient intake levels for the purpose of improving MS risk factors. The participants in this study were 512 adults consisting of 271 men and 241 women aged 30 and over, who visited a public health center for a medical check up. The diagnosis of MS subjects was adapted from the NCEP-ATPIII guidelines and the WHO Asia-Pacific Area criteria for obesity. The MS group was defined as subjects displaying three or more risk factors, and the non MS group was defined as those displaying two or less risk factors. A dietary survey was conducted using the 24-hour recall method. The number of subjects displaying MS syndrome factors was 158 (30.9%), broken down into, 89 men and 69 women. Regarding risk factors in the MS group, the prevalence of waist circumference was 40.5%, hypertension 34.2%, hyperglycemia 31.0%, low HDL-cholesterol 24.7%, and hypertriglycemia 19.6%. BMI, sistolic blood pressure, blood glocose, blood triglyceride, and blood HCL-cholesterol of the MS group were significantly higher compared to the non MS group. Male subjects in the MS group reported high intakes of cereals, sugar, fruits, meat and poultry, oil and fats, and beverages and total food intake was significantly higher compared to the non MS group. Women in the MS group reported high intakes of meat and poultry, milk and dairy products, beverages, and seasonings, and total food intake was higher compared to the non MS group. Dietary diversity score (DDS) was 3.82~4.04, which was not significant among the groups. In men, dietary variety score (DVS) was 16.3 in the MS group and 19.4 in the non MS group, whereas in women, the DVS was 15.2 in the non MS group and 17.0 in the MS group. In GMVDF pattern, 11111 pattern was 30.7%, followed by 01111 for men and 11101 for women. Calorie, fat, and cholesterol intakes in men as well as, calorie, fat, and folate intakes in women in the MS group were higher compared to the non MS group. Intakes of protein, P, Fe, Na, vitamin $B_1$, vitamin $B_2$, niacin, vitamin E, and Zn were higher than the KDRIs. On the other hand, intakes of Ca, K, fiber, vitamin $B_2$, and vitamin C were below the KDRIs. Intakes of lipids, animal food, Na, and cholesterol in the MS group were higher compared to the non MS group, whereas intake of dietary fiber was lower. Our results indicate that continuous, systematic nutritional education program must implemented to reduce the risk factors associated with MS.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.33 no.10
• /
• pp.1634-1640
• /
• 2004

This study was designed to compare the nutritional intake and iron nutritional status between urban and rural middle school girls. Along with a questionnaire, blood samples were obtained from 311 middle school girls (urban 129 girls, rural 182 girls). Nutrient intakes were measured with a convenient method, and clinical symptoms relating anemia was investigated by 4-point Likert scale. For the nutrient intake, the total energy intake was 1722.2 kcal (82.0% of RDA) for the urban group and 1649.5 kcal (78.6% of RDA) for rural group. The rural group showed significantly lower level than the urban group in all nutrients except fat, carbohydrate and total energy intake. Regarding the food frequency, students from the rural group marked significantly lower intake of milk (p<0.00l), kimchi (p<0.05), fruit (p<0.05), tofu, bean (p<0.00l) than the urban group. For every clinical finding regarding anemia, the rural group marked higher value than the urban group but the difference was not significant. The hemoglobin concentration of urban group was 13.28 g/dL, and rural group showed 12.51 g/dL which was significantly lower than urban group (p<0.00l). The hematocrit rate was 37.82% for the urban group and 38.13% for the rural group and there was no significant difference between two groups. The red blood cell (RBC) count of the rural group was significantly lower than the urban group (p<0.00l). Evaluating with the iron deficiency standard which is less than 12 g/dL, the urban group was 6.2% and the rural group was 34.6% thus the deficiency rate was significantly higher in the rural group. This study showed that nutrient and iron status of the girls of rural group is not as good as the urban group. As middle school girls require high level of iron absorption due to blood loss which occurs during abrupt physical growth and menstruation, dietary counselling is required to enhance the iron status. When iron deficiency is serious, they need to take more positive action such as iron supplement in addition to food-iron fortification.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.34 no.7
• /
• pp.987-999
• /
• 2005

The purpose of this study was to evaluate the effect of short-term nutrition education camp on food and nutrient intakes of obese children. The subjects of the study were 30 obese children in Gumi city who have obesity index over $130\%$. The food consumption of the subjects was surveyed for three days before the camp, for eleven days during the first camp and for three days after the second camp, by food record method. The mean intakes of energy and carbohydrates in obese children were significantly decreased during and after the nutrition education camp, and that of vitamin C was significantly increased after the camp. The mean daily total food intake of the subjects was gradually decreased from 1646.4g before the camp to 1438.6g during the camp and 1412.66g after the camp. Energy and fat intake ratios from grains and milks were significantly decreased after the camp compared with that before the camp, and the energy intake ratio from grains, milks and eggs was significantly low during the camp. The protein intake ratios from grains, potatoes, vegetables and fishes were significantly increased after the camp. The calcium intake ratios from potatoes and milks were significantly increased during and after the camp, and the ratio from eggs was significantly decreased after the camp. The iron intake ratios from potatoes and fishes were significantly increased during and after the camp, and the ratio from grains was significantly low during the camp. The results of the study demonstrated that the short-term nutrition education program positively affected the overall food consumption and nutrients intakes of obese children.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.36 no.9
• /
• pp.1148-1160
• /
• 2007

This study was performed to document the association between eating behaviors and major risk factors for cardiovascular diseases. Those who stated that they ate a daily breakfast for male and female were 88.6% and 96.0%, $1{\sim}2$ times a week were 9.1% and 2.0%, $3{\sim}4$ times a week were 2.3% and 2.0%, respectively. Those who stated that they were overeating of $0{\sim}1$ time a week for man and female were 80.7% and 89.9%, overeating of $2{\sim}3$ times a week were 19.3% and 10.1%, respectively. Those who said that they were regular of meal time for man and female were 38.6%, and 37.4%, sometimes irregular of meal time were 14.8% and 19.2%, irregular of meal time were 46.6% and 43.4%, respectively. Those who said that they were light of eating volume for man and female were 20.5% and 25.3%, moderate of eating volume were 69.3% and 61.6%, heavy of eating volume were 10.2% and 13.1%, respectively. Those who said that they were very fast of eating speed for man and female were 15.9% and 8.1%, fast of eating speed were 51.1% and 34.3%, moderate of eating speed were 4.5% and 20.2%, slow of eating speed were 17.0% and 14.1%, and very slow of eating speed were 11.4% and 23.2%, respectively. Higher frequency of breakfast a week resulted in higher serum total cholesterol and blood sugar for the daily eating group for both genders with women having high LDL-cholesterol and HDL-cholesterol. Both group had high HDL-cholesterol and low blood sugar with less number of overeating, with men having low triglyceride and LDL-cholesterol. With regular meal, both group had low triglyceride, total-cholesterol, atherogenic index, and blood sugar with women having low LDL-cholesterol. For both groups, the triglyceride, total-cholesterol, LDL-cholesterol, atherogenic index, and blood sugar had higher figures for overeating, with men having low HDL-cholesterol and women having high HDL-cholesterol. This study revealed that less number of overeating, regular mealtime, and less volume of food intake are effective in preventing and treating for the cardiovascular diseases.