• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.51-58
• /
• 2022

In this paper, we propose a decision tree-based machine learning model that leads to food exchange table renewal by classifying food groups through machine learning for existing food and food data found by web crawling. The food exchange table is the standard for food exchange intake when composing a diet such as diet and diet, as well as patients who need nutritional management. The food exchange table, which is the standard for the composition of the diet, takes a lot of manpower and time in the process of revision through the National Health and Nutrition Survey, making it difficult to quickly reflect food changes according to new foods or trends. Since the proposed technique classifies newly added foods based on the existing food group, it is possible to organize a rapid food exchange table reflecting the trend of food. As a result of classifying food into the proposed model in the study, the accuracy of the food group in the food exchange table was 97.45%, so this food classification model is expected to be highly utilized for the composition of a diet that suits your taste in hospitals and nursing homes.

• Journal of agricultural medicine and community health
• /
• v.38 no.3
• /
• pp.182-194
• /
• 2013

Objectives: To identify and compare the health behaviors and health status of the elderly between urban and rural areas using the data of the Korean National Health and Nutrition Examination Survey (KNHANES). Methods: The study population comprised 3,823 elderly people aged 65 years or older who participated in the $4^{th}$ KNHANES (2007-2009). The areas were classified into "large cities," "cities," and "rural areas" using the administrative and residential areas. The health behaviors and health status of the elderly between the rural and urban areas were compared using a complex sample design with the Rao-Scott chi-square test and weighted multiple logistic regression analysis. Results: Compared to large cities, the odds ratios (ORs) (95% confidence interval [CI]) of rural areas were as high as 1.58 (1.25-2.01) for the influenza vaccination and as low as 0.47 (0.37-0.59) for flexibility exercises, 0.56 (0.38-0.81) for muscular exercises, and 0.76 (0.62-0.92) for obesity. The ORs (CI) for osteoarthritis and diabetes mellitus were as low as 0.81 (0.66-0.99) and 0.70 (0.55-0.89), respectively. Conclusions: The health behaviors and health status of the elderly are better in rural areas than in urban areas despite the fact that the socioeconomic conditions in rural areas are poorer that those in urban areas. These findings suggest that programs suitable for residential areas should be developed and that studies to explain the differences in residential areas are needed.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.573-585
• /
• 2018

In this study, we fit the logistic regression model and naïve Bayesian classifier model using 11 risk factors to predict the incidence rate probability for type 2 diabetes mellitus. We then introduce how to construct a nomogram that can help people visually understand it. We use data from the 2013-2015 Korean National Health and Nutrition Examination Survey (KNHANES). We take 3 interactions in the logistic regression model to improve the quality of the analysis and facilitate the application of the left-aligned method to the Bayesian nomogram. Finally, we compare the two nomograms and examine their utility. Then we verify the nomogram using the ROC curve.

• Journal of Digital Convergence
• /
• v.16 no.2
• /
• pp.251-259
• /
• 2018

This study aimed to identify the risk factors for cardiovascular disease (CVD) among age groups using the Framingham risk score (FRS). The research design used was a cross sectional descriptive study using the Sixth Korean National Health and Nutrition Examination Survey from 2013-2015. Data from 5211 men, between the ages of 30-74 was analyzed. After adjusting for age, the result of logistic regression analysis showed that obesity (OR=2.51 95% CI=2.05-3.07), physical inactivity (OR=1.71, 95% CI=1.39-2.10), heavy alcohol drinking (OR=1.33, 95% CI=1.09-1.62), and dietary fiber intake (OR=0.99, 95% CI=0.98-0.99) were presented as predictors of CVD. Obesity was considered to be a particularly important predictor of CVD for young and middle-aged men. This result will be used for developing intervention relating to lifestyle modification for young and middle-aged men.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.555-567
• /
• 2020

Hypertension has a steadily increasing incidence rate as well as represents a risk factors for secondary diseases such as cardiovascular disease. Therefore, it is important to predict the incidence rate of the disease. In this study, we constructed nomograms that can predict the incidence rate of hypertension. We use data from the Korean National Health and Nutrition Examination Survey (KNHANES) for 2013-2016. The complex sampling data required the use of a Rao-Scott chi-squared test to identify 10 risk factors for hypertension. Smoking and exercise variables were not statistically significant in the Logistic regression; therefore, eight effects were selected as risk factors for hypertension. Logistic and Bayesian nomograms constructed from the selected risk factors were proposed and compared. The constructed nomograms were then verified using a receiver operating characteristics curve and calibration plot.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.295-299
• /
• 2018

The aim of this study was to evaluate the association between the level urine cotinine and periodontal diseases in Korea adults. The date from the 2014, 2015 Korean National Health and Nutrition Survey were used, and 5,146 subjects over 30 years were included in the analysis. Periodontal disease was assessed using the Community Periodontal Index. Binary logistic regression model was used to estimate the odds ratio with 95% confidence intervals. There was a 2.08-fold (95% CI; 1.73-2.05) increased in the odds of periodontal disease for those with any ETS exposure compared with those with non-smokers following adjustment for sex, age, education, and income. The level of urine cotinine also showed a dose-dependent increase in extent of periodontal disease. Among persons in the Korea who had never used tobacco, those exposed to ETS were more likely to have periodontal disease than were those not exposed to ETS. In the future, voluntary compliance of smokers to measures to reduce ETS exposure should be encouraged.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.257-264
• /
• 2019

This study was to investigate the relationship between the smoking status and the number of tooth loss according to the daily average smoking amount of the elderly in Korea using the raw data of the 6th National Health and Nutrition Survey. The study subjects were 4,037 elderly people aged 65 or older. As a result, it was found that 2.35 times more severe heavy smoking in the past, 3.01 times in the current light smoker, 3.27 times in the current heavy smoker, Respectively. This study confirmed that there is a difference in the risk of tooth loss according to the average daily smoking amount. Therefore, in order to increase and maintain the residual teeth as much as possible, it can be suggested as an objective data of smoking cessation treatment at the dental clinic and contribute to motivation.

• Korean Journal of Clinical Laboratory Science
• /
• v.48 no.3
• /
• pp.183-187
• /
• 2016

The aim of this study was to assess the association between microalbumin and pulse pressure (PP) in Korean adults. The study subjects were Korean adults 20 years or older (n=4,948) who participated in the Korea National Health and Nutrition Examination Survey 2012. The urine microalbumin level ($M{\pm}SE$) was significantly higher (p=0.047) in the high PP group (PP>60.0 mmHg) [$33.02{\pm}4.93{\mu}g/mL$ (95% confidence interval (CI), 23.37~42.68)] than the normal PP group ($PP{\leq}60.0mmHg$) [$22.57{\pm}1.63{\mu}g/mL$ (95% CI, 19.36~25.77)], after adjusting for age, gender, smoking, drinking, regular exercising, WM, BMI, TC, TG, HDL-C, FBG, BUN, creatinine, and urine creatinine. In conclusion, pulse pressure was associated with the microalbumin level in Korean adults.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.619-630
• /
• 2019

Dyslipidemia is a representative chronic disease affecting Koreans that requires continuous management. It is also a known risk factor for cardiovascular disease such as hypertension and diabetes. However, it is difficult to diagnose vascular disease without a medical examination. This study identifies risk factors for the recognition and prevention of dyslipidemia. By integrating them, we construct a statistical instrumental nomogram that can predict the incidence rate while visualizing. Data were from the Korean National Health and Nutrition Examination Survey (KNHANES) for 2013-2016. First, a chi-squared test identified twelve risk factors of dyslipidemia. We used a naïve Bayesian classifier model to construct a nomogram for the dyslipidemia. The constructed nomogram was verified using a receiver operating characteristics curve and calibration plot. Finally, we compared the logistic nomogram previously presented with the Bayesian nomogram proposed in this study.

• Clinical and Experimental Pediatrics
• /
• v.51 no.12
• /
• pp.1300-1309
• /
• 2008

Purpose :This study aimed to estimate age- and gender-specific cut points for metabolic syndrome (MS) components, including body mass index (BMI), blood pressure (BP), triglycerides, high-density lipoprotein (HDL) cholesterol, and glucose. Methods :Data from the 1998, 2001, and 2005 Korean NHANES (National Health and Nutrition Examination Survey) were analyzed (n=4164; 2,139 boys and 2,025 girls, aged 10-19 years). Height, weight, waist circumference (WC), BP, triglycerides, HDL cholesterol, and fasting glucose were measured. Results :BMI over $25kg/m^2$ represents the $85^{th}P$ (percentile) in 17-year-old boys and the $90^{th}P$ in 17-year-old girls. A level of WC higher than that of the cutoff points of Asian adults was found in the $90^{th}P$ of 17-year-old boys and girls. The $90^{th}P$ of boys aged 15 years old and the $95^{th}P$ of 13-year-old were included in the range of systolic BP over 130 mm Hg. Over the $75^{th}P$ of the group showed triglycerides greater than 110 mg/dL, (criterion of MS presented by NCEP-ATP III) and the $90^{th}P$ of the group showed triglycerides greater than 150 mg/dL by IDF. An HDL cholesterol level of 40 mg/dL represents the $25^{th}P$ in boys and the $10^{th}P$ in girls. A glucose level greater than 110 mg/dL represents the $95^{th}P$ and greater than 100 mg/dL represents the $90^{th}P$. Conclusion :Values of the $90^{th}P$ of MS components in late adolescent boys (WC, BP, and triglycerides) and girls (WC and triglycerides) were very high and in close proximity to the diagnostic criteria of adult MS.