• The Journal of Korean Society for School & Community Health Education
• /
• v.15 no.3
• /
• pp.43-54
• /
• 2014

Objectives: The purpose of this study was to find out the relation factors of weight control behaviors, mental health status and body image perception in adolescents and to use basis data of health promotion for adolescents. Methods: This study used data from the Fifth Korea National Health and Nutrition Examination Survey (KNHANES V-2, 2011). The subjects were 653 between 12-19 age. Data analysis was done with SPSS/WIN 19.0 using Chi-square test, and Logistic regression. Results: The result is as follows. The case of female adolescents, abnormal perception of body image was significantly higher on weight reduction effort and normal weight, low weight in BMI. The case of male adolescents, abnormal perception of body image was higher on normal weight in BMI. Conclusions: The adolescents tend to do unreasoning weight loss behavior without properly perception for their body image. Therefore, we suggest that adolescents be provided social support for positive body image and be developed perception program with the importance of inner values.

• Journal of the Korean Society of School Health
• /
• v.30 no.3
• /
• pp.317-324
• /
• 2017

Purpose: Breakfast is the most important meal to provide energy for the day. Breakfast is especially important to give enough nutritional support to children and adolescents for their physical growth and sexual development. Sleep-related factors like average sleep duration and wake up time would mostly be associated with regular breakfast. This study aimed to investigate the effect of sleep on regular breakfast consumption in Korean adolescents. Methods: The study used the data from the 12th Korea Youth Risk Behavior Web-based Survey (KYRBS-XII) conducted in 2016 by the Korea Centers for Disease Control and Prevention. The data of 62,820 subjects (middle/high school students) were included in the final analysis. The study examined the factors related to regular breakfast, focusing on weekday average sleep duration and wake up time of middle school students and high school students, respectively. Results: Regular breakfast consumption was shown to have a statistically significant association with high economic status, nutritional education, weekday average sleep duration, wake up time, and subjective sleep satisfaction in the multivariate logistic regression. Regardless of the school level, regular breakfast consumption was significantly associated with early wake up time. As to the effect of weekday average sleep duration on regular breakfast consumption, it showed some different results depending on the school level. Conclusion: Regular breakfast consumption of Korean adolescents was related to weekday average sleep duration and wake up time. Having breakfast regularly was affected by both adequate weekday average sleep duration and early wake up time.

• Safety and Health at Work
• /
• v.12 no.3
• /
• pp.370-376
• /
• 2021

Backround: Working condition surveys are widely recognized as useful tools for monitoring the quality of working life and the improvements introduced by health and safety policy frameworks at the European and national level. The Italian Workers' Compensation Authority carried out a national survey (Insula) to investigate the employer's perceptions related to working conditions and their impact on health. Methods: The present study is based on the data collected from the Italian survey on health and safety at work (INSULA) conducted on a representative sample of the Italian workforce (n = 8,000). This focuses on the relationship between psychosocial risk factors and self-reported health using a set of logistic and linear regression models. Results: Working conditions such as managerial support, job satisfaction, and role act as protective factors on mental and physical health. On the contrary, workers' risk perceptions related to personal exposure to occupational safety and health risks, concern about health conditions, and work-related stress risk exposure determine a poorer state of health. Conclusions: This study highlights the link between working conditions and self-report health, and this aims to provide a contribution in the field of health at work. Findings show that working conditions must be object of specific preventive measures to improve the workers' health and well-being.

• Journal of Preventive Medicine and Public Health
• /
• v.54 no.5
• /
• pp.309-316
• /
• 2021

Objectives: This study examined stunting at birth and its associations with physical factors of parents and children in Indonesia. Methods: This study analyzed secondary data from the national cross-sectional Indonesian Basic Health Survey 2018, conducted across 34 provinces and 514 districts/cities. Birth length data were available for 756 newborns. Univariable, bivariable, and multivariable logistic regression analyses were performed to determine associations between the physical factors of parents and children and stunting at birth. Results: In total, 10.2% of children aged 0 months were stunted at birth (10.7% of males and 9.5% of females). Stunting at birth was associated with the mother's age at first pregnancy, parity, parents' heights, parents' ages, and gestational age. Children from mothers with short statures (height <145.0 cm) and fathers with short statures (height <161.9 cm) had an almost 6 times higher likelihood of being stunted at birth (adjusted odds ratio, 5.93; 95% confidence interval, 5.53 to 6.36). A higher maternal age at first pregnancy had a protective effect against stunting. However, other variables (firstborn child, preterm birth, and both parents' ages being <20 or >35 years) corresponded to a 2-fold higher likelihood of stunting at birth compared to the reference. Conclusions: These findings provide evidence that interventions to reduce stunting aimed at pregnant females should also consider the parents' stature, age, and parity, particularly if it is the first pregnancy and if the parents are short in stature or young. Robust programs to support pregnant females and monitor children's heights from birth will help prevent intergenerational stunting.

• Safety and Health at Work
• /
• v.11 no.4
• /
• pp.491-499
• /
• 2020

Background: Assembly lines work is frequently associated to work-related upper limb musculoskeletal disorders. The related disability and absenteeism make it important to implement efficient health surveillance systems. The main objective of this study was to identify self-reported variables that can determine work-related upper limb musculoskeletal symptoms-discomfort/pain-during a 6-month follow-up. Methods: This was a prospective study with a 6-month follow-up period, performed in an assembly line. Upper limb musculoskeletal discomfort/pain was assessed through the presence of self-reported symptoms. Uni- and multivariate logistic regression analyses were used to evaluate which self-reported variables were associated to upper limb symptoms after 6 months at the present and to upper limbs symptoms in the past month. Results: Of the 200 workers at baseline, 145 replied to the survey after 6 months. For both outcomes, "having upper limb symptoms during the previous 6 months" and "education" were possible predictors. Conclusion: Our results suggest that having previous upper limb symptoms was related to its maintenance after 6 months, sustaining it as a specific determinant. It can be a hypothesis that this population had mainly workers with chronic symptoms, although our results give only limited support to self-reported indicators as determinants for upper limb symptoms. Nevertheless, the development of an efficient health surveillance system for high demanding jobs should implicate self-reported indicators, but also clinical and work conditions assessment should be accounted on the future.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Safety and Health at Work
• /
• v.12 no.4
• /
• pp.432-438
• /
• 2021

Background: We aimed to investigate the prevalence of low back pain (LBP) and its associated agricultural work-related, biomechanical factors among this population. Methods: We analyzed initial survey data from the Safety for Agricultural Injury of Farmers cohort study involving adult farmers in Jeju Island. The prevalence of LBP was calculated with associated factors. Results: In total, 1,209 participants were included in the analysis. The overall prevalence of LBP was 23.7%. Significant associations for LBP were the type of farming activity, length of farming career, prior agricultural injury within 1 year, and stress levels. Multivariate logistic regression analysis revealed three biomechanical factors significantly related to LBP: repetitive use of particular body parts; the inappropriate posture of the lower back and neck. Conclusions: Some occupational, and biomechanical risk factors contribute to LBP. Therefore, postural education, injury prevention education, and psychological support will be needed to prevent LBP.

• Neurospine
• /
• v.15 no.4
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.549-559
• /
• 2018

The purpose of this study was to investigate the risk factors of pregnancy and the relationship between pregnancy experience and suicidal behavior in 284 pregnancy experienced adolescents aged 13-19 years. The suicidal ideation was 57.8%, the suicide plan was 37.7% and the suicide attempt was 37.3% among female adolescents with pregnancy experience. By multivariate logistic regression analysis, female adolescents who experienced pregnancy had 1.44 times more suicidal ideation, 2.39 times more suicide plans, and 2.38 times more suicide attempts than those without suicidal thoughts, plans and attempts. Because of the high correlation between pregnancy experience and suicidal behavior in female adolescents, school and education authorities need systematic education and countermeasures to prevent adolescents' pregnancy and risk of suicide after pregnancy. And above all, convergent support and interest in home, school and community comprehensive area should be supported.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.71-78
• /
• 2019

This study aims to identify good borrowers within the context of P2P lending. P2P lending is a growing platform that allows individuals to lend and borrow money from each other. Inherent in any loans is credit risk of borrowers and needs to be considered before any lending. Specifically in the context of P2P lending, traditional models fall short and thus this study aimed to rectify this as well as explore the problem of class imbalances seen within credit risk data sets. This study implemented an over-sampling technique known as Synthetic Minority Over-sampling Technique (SMOTE). To test our approach, we implemented five benchmarking classifiers such as support vector machines, logistic regression, k-nearest neighbor, random forest, and deep neural network. The data sample used was retrieved from the publicly available LendingClub dataset. The proposed SMOTE revealed significantly improved results in comparison with the benchmarking classifiers. These results should help actors engaged within P2P lending to make better informed decisions when selecting potential borrowers eliminating the higher risks present in P2P lending.