| Yang-Im Hur | 5 Articles |
Background
Predicting the risk of osteoporotic fractures is vital for prevention. Traditional methods such as the Fracture Risk Assessment Tool (FRAX) model use clinical factors. This study examined the predictive power of the FRAX score and machine-learning algorithms trained on FRAX parameters. Methods We analyzed the data of 2,147 female participants from the Ansan cohort study. The FRAX parameters employed in this study included age, sex (female), height and weight, current smoking status, excessive alcohol consumption (>3 units/d of alcohol), and diagnosis of rheumatoid arthritis. Osteoporotic fracture was defined as one or more fractures of the hip, spine, or wrist during a 10-year observation period. Machine-learning algorithms, such as gradient boosting, random forest, decision tree, and logistic regression, were employed to predict osteoporotic fractures with a 70:30 training-to-test set ratio. We evaluated the area under the receiver operating characteristic curve (AUROC) scores to assess and compare the performance of these algorithms with the FRAX score. Results Of the 2,147 participants, 3.5% experienced osteoporotic fractures. Those with fractures were older, shorter in height, and had a higher prevalence of rheumatoid arthritis, as well as higher FRAX scores. The AUROC for the FRAX was 0.617. The machine-learning algorithms showed AUROC values of 0.662, 0.652, 0.648, and 0.637 for gradient boosting, logistic regression, decision tree, and random forest, respectively. Conclusion This study highlighted the immense potential of machine-learning algorithms to improve osteoporotic fracture risk prediction in women when complete FRAX parameter information is unavailable. Citations Citations to this article as recorded by
Youth suicide is increasingly being recognized as a major social problem in South Korea. In this study, we aimed to explore the effects of parental support on the relationship between life stress and suicidal ideation among middle-school students. This study analyzed data from a cross-sectional study on mental health conducted by the South Korea National Youth Policy Institute between May and July of 2013. Questionnaire responses from 3,007 middle-school students regarding stress factors, thoughts of suicide during the past year, and parental support were analyzed in terms of 3 subscale elements: emotional, academic, and financial support. Among the participants, 234 male students (7.8%) and 476 female students (15.8%) reported experiencing suicidal ideation in the past year. Life stress significantly influenced suicidal ideation (P<0.001), and parental support and all of the subscale elements had a significant influence on decreasing suicidal ideation. As shown in model 1, life stress increased suicidal ideation (adjusted odds ratio [aOR], 1.318; P<0.001), and, in model 2, the effect of life stress on suicidal ideation decreased with parental support (aOR, 1.238; P<0.001). Parental support was independently related to a decrease in suicidal ideation, and life stress was independently related to an increase in suicidal ideation. Parental support buffered the relationship between life stress and suicidal ideation. Citations Citations to this article as recorded by
With metabolic syndrome (MS) being a major risk factor for cardiovascular disease, and central obesity being a major predisposing factor for MS, intensive research is currently being performed on cutoff values according to race and sex. Menopause is an especially significant factor in designating cutoff values for female central obesity, as menopause brings sudden bodily changes that induce central obesity and increased prevalence of MS. Therefore this study aimed to investigate the cutoff values for the obesity index and its validity in predicting the criteria for MS in Korean women according to menstrual status. The study focused on 3,103 women 20 years of age or older participating in the 2007 Korea National Health and Nutrition Examination Survey. Definitions of non-adipose components of MS were defined by the International Diabetes Federation, and menstrual status was judged on the basis of survey results. The sensitivity, specificity, and positive and negative predictive values of the central obesity index (body mass index [BMI], waist circumference [WC], waist-to-height ratio [WHtR]) according to menstrual status for two or more non-adipose components of MS were calculated based on the Youden index. Area under the curve (AUC) values predicting the presence of two or more metabolic risk factors were higher in pre-menopausal women, with AUC values for BMI, WC, and WHtR being, in pre- and post-menopausal women, 23.1 kg/m2 vs. 23.9 kg/m2, 76.1 cm vs. 82.5 cm, and 0.49 vs. 0.53, respectively. The WC cut off (76 cm) for pre-menopausal women was found to be more sensitive and more effective at screening for MS risks than the cutoff value given by the Korea Society for the Study of Obesity. The central obesity index showed better predictability for MS risk in pre-menopausal women. Because the central obesity index cutoff values are lower in pre-menopausal women, the possibility of metabolic risk can be considered for pre-menopausal women with WC lower than 85 cm. Assessment and control of other risks are needed accordingly for preventing the development of MS. Citations Citations to this article as recorded by
While smoking prevalence in Korean men has been decreasing, it is increasing in Korean women. Little is known about women's smoking inequalities in Korea. This study was conducted to investigate the association of socioeconomic indicators with the initiation and cessation of smoking among Korean women. This was a cross-sectional study on 9,089 women aged 25-64 years from the 2008 Seoul Community Health Survey. The data on smoking and socioeconomic status were obtained through face-to-face interviews. Smoking initiation rate was defined as the proportion of the individuals who had started smoking at least one cigarette among all subjects. Smoking cessation rate was calculated by dividing the number of individuals who had quit smoking by the number of ever smokers. Education level, total family income and occupation were investigated as socioeconomic indicators. Education level was significantly associated with both initiation and cessation of smoking. Lower educated women had a higher likelihood of smoking initiation (odds ratio [OR], 1.72; 95% confidence interval [CI], 1.17 to 2.51) but lower likelihood of smoking cessation (OR, 0.38; 95% CI, 0.22 to 0.66) than higher educated women. Smoking initiation rate was higher in manual workers (OR, 1.65; 95% CI, 1.20 to 2.27) than in non-manual workers. However, there were no significant differences of both initiation and cessation of smoking according to total household income. This study shows that there are smoking inequalities among Korean women. It is thought that education level and occupation are important determinants of women's smoking status. Citations Citations to this article as recorded by
Recently, it has been reported that gamma-glumyltransferase (GGT) is associated with various cardiovascular risk factors including overweight in adults. However, there are few studies on the relationship between GGT and cardiovascular risk factors in children. The aim of this study was to assess the relationship between serum GGT level and overweight in Korean urban children. This study was a cross-sectional study using data on 390 4th grade students of elementary schools in Gunpo, Korea. Children were divided into 4 groups according to gender-specific quartiles of serum GGT level. Body mass index, waist circumference and body fat percentage were quantified as adiposity indices. All adiposity indices in children of the highest GGT level quartile were higher than those in children of the lowest quartile. Adjusted odd ratios on overweight of the highest quartile of GGT level compared to the lowest quartile were 14.40 (95% confidence interval [CI], 4.43 to 46.83) in boys and 2.94 (95% CI, 1.06 to 8.16) in girls. This study shows that high serum GGT level is related with overweight in Korean urban children and this relationship is stronger in boys compared to girls. Citations Citations to this article as recorded by
|
|
