• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.581-588
• /
• 2017

This study was conducted to determine which factors would predict metabolic syndrome (MetS) perception and exercise by applying a machine learning classifier, or Extreme Gradient Boosting algorithm (XGBoost) from July 2014 to December 2015. Data were obtained from the Korean Community Health Survey (KCHS), representing different community-dwelling Korean adults 19 years and older, from 2009 to 2013. The dataset includes 370,430 adults. Outcomes were categorized as follows based on the perception of MetS and physical activity (PA): Stage 1 (no perception, no PA), Stage 2 (perception, no PA), and Stage 3 (perception, PA). Features common to all questionnaires for the last 5 years were selected for modeling. Overall, there were 161 features, categorical except for age and the visual analogue scale (EQ-VAS). We used the Extreme Boosting algorithm in R programming for a model to predict factors and achieved prediction accuracy in 0.735 submissions. The top 10 predictive factors in Stage 3 were: age, education level, attempt to control weight, EQ mobility, nutrition label checks, private health insurance, EQ-5D usual activities, anti-smoking advertising, EQ-VAS, education in health centers for diabetes, and dental care. In conclusion, the results showed that XGBoost can be used to identify factors influencing disease prevention and management using healthcare bigdata.

• Journal of Technologic Dentistry
• /
• v.35 no.2
• /
• pp.157-171
• /
• 2013

Purpose: This study aims to present a database for the development of a healthcare management program based on the survey and analysis of self reported psychosomatic symptoms among the current dental technology students. Methods: Subjects of our study are 480 dental technology major students enrolled in a third year college located Gyeonggi, Chungcheong, and Gangwon province. Using a random sampling, we conducted a self-report survey from August 30, 2011 to October 28, 2011 and 418 reports were collected as feedback and we put an analysis on them. Results: 1. The average physical self symptom was 20.49, which is higher than the average mental self symptom(18.54). Of the subcategories of psychosomatic self symptom, we observed multiple subjective symptoms as the highest one(37.77), and aggression as the lowest(13.77). 2. As to gender, both physical and mental self symptom were statistically significant with the scale score of(p<.001). The scale score of subcategories is as follows; multiple subjective symptoms(I, p<.001), eye and skin(B, p<.001), digestive(C, p<.001), impulsiveness(H, p<.001), lie scale(L, p<.001), mental instability(J, p<.001), depression(K, p<.001), aggression(F, p<.001), irregularity of life(G, p<.001), mouth and anal(D, p<.05), nervousness(E, p<.05). 3. As for obesity, statistical significance was shown with the scale scores of physical self symptom(p<.001), multiple subjective symptoms(I, p<.001), digestive(C, p<.001), aggression(F, p<.001), depression(K, p<.01), irregularity of life(G, p<.01), respiratory(A, p<.05), eye and skin(B, p<.05), impulsiveness(H, p<.05), mental instability(J, p<.05). The scale scores in the environmental quality and life satisfaction were shown as follows; depression(K, p<.001), lie scale(L, p<.01), and irregularity of life(G, p<.05). 4. We employed multiple regression analysis to take account of general factors affecting psychosomatic self symptoms, and drew that the explanatory power of the model was proved with the scales of physical self symptom(4.1%) and mental self-symptom(3.6%). Obesity was a factor that affects physical self symptom with the scale score of(p<.01), and environmental quality and life satisfaction(p<.01) and obesity(p<.05) affect mental self symptom. Conclusion: In this analysis we observed obesity of dental technology students can influence their psychosomatic self symptoms. In this sense, it would be reasonable to develop a healthcare management and education programs that help the students maintain a healthy weight and promote their health.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.127-136
• /
• 2020

This study investigated the correlation between the participation in health-related decisions and self-care competency and the factors influencing self-care competence of patients with chronic disease. The participants were 518 patients with chronic illnesses who were admitted to a public health center. Using a structured-questionnaire, the data was collected from January 1, 2019 to 31, 2019. The data was analyzed using descriptive statistics, t-tests, ANOVA, Scheffé tests, Pearson correlation coefficients and multiple linear regression with the IBM SPSS/WIN 22.0 program. The mean scores on the participation in health-related decisions and self-care competency were 3.62±0.20 and 4.57±0.34, respectively. The main variables that distinguish significant differences between participation in healthcare decisions and self-care capabilities are gender, age, education level, diagnosis, and subjective health status. Self-care competency was positively correlated with the participation in health-related decisions (r=.66, p=.043). Factors influencing self-care competence were education (β=-2.23, p<.001), health concerns (β=0.14, p=.003), subjective health statues (β=2.57, p=.011), and age (β=-0.36, p=.048). The input variables explained .56 of self-care competence. The results of the study indicate that approaches focusing on enhancing the participation in health-related decisions could potentially improve self-care competency of patients with chronic disease.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1197-1210
• /
• 2017

This study aimed to compare premature ejaculation and erectile function according to penile characteristics. 99 adult men responded to a questionnaire on penile characteristics, premature ejaculation and erectile function. In the questionnaire survey, 69 questionnaires were analyzed except missing or incomplete answers. All collected data were analyzed by independent t test, Chi-square test using SPSS 22. Glans > penis type showed significant differences in subjective premature ejaculation and objective premature ejaculation compared to Glans ${\frac{._-}{.}$ penis type (p <.05). Men with subjective premature ejaculation showed significant differences in objective premature ejaculation, treatment intent, and satisfaction compared to men without subjective premature ejaculation (p <.05). Presence of objective premature ejaculation, presence of treatment intent, and marital status were significantly different in satisfaction (p <.05). In economic status, high was significantly different in confidence for erectile function compared to middle or low (p <.05). The results of this study suggest that the premature ejaculation and erectile function according to the penile characteristic may be different and may be used as a basis for the development of an intervention program for sexual rehabilitation of men with premature ejaculation and erectile dysfunction.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.343-352
• /
• 2021

A convergence study was conducted to develop a smartphone application for self-practice of core nursing skills and evaluate its usefulness for undergraduate nursing students. Mobile Application Rating Scale and seven essay questionnaire were used to for usability evaluation among 22 undergraduate nursing students. The score of the information domain was the highest with 4.19(SD 0.79). The subjective quality domain showed the lowest score of 3.08(SD 0.87). Participants' performance confidence score was 8.23(SD 1.60), and learning satisfaction score was 7.89(SD 0.87). Participants reported that the convenience and repetitive self-learning were the strengths of the app. In addition, design and technical supplementation, and lecturer-feedback would improve effectiveness of the current educational app. Findings of this convergent study would be helpful to promote the application of mobile apps for effective self-learning of core nursing skills in undergraduate nursing education. Future resesarch is needed to examine effectiveness study of mobile app on the performance of core nursing skills.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.2
• /
• pp.7-22
• /
• 2021

Objective : This study aimed to analyze the effect of transcranial direct current stimulation (tDCS) on cognitive function recovery in patients with stroke. Methods : Data published in Korean and foreign academic journals from 2009 to 2019 were searched using the NDSL, RISS, PubMed, and CINAHL databases. A total of 11 experimental research articles were selected based on the inclusion and exclusion criteria. A qualitative assessment was conducted, and a meta-analysis of nine results from seven of the stuides was performed using the Comprehensive Meta-Analysis 3.0 program. Results : Based on the results of the meta-analysis, the attention and memory effect sizes were 0.725 and 0.796, respectively, which were both considered a "medium effect size". Statistically significant changes were observed in both the areas (p<0.05). Conclusion : The results of this study confirmed that tDCS can be useful in the rehabilitation of patients with stroke with limited cognitive function. In addition, the application methods differed, indicating that a formalized tDCS protocol is required.

• Journal of agricultural medicine and community health
• /
• v.45 no.4
• /
• pp.194-207
• /
• 2020

Purpose: The purpose of this study is to develop and evaluate the curriculum, that was the continuing professional development program, for cultivating physician's competencies in public health. Methods: This study was conducted through in-depth interview and survey in the frame of ADDIE, from 2 May to 30 June in 2019. Participants were 7 physicians by in-depth interview and Respondents were 46 physicians worked in public health by survey. Results: The results were analyzed and described in the frame of ADDIE model. In the stage of Analysis, physician's core competencies in public health was presented to practical education, management of organization and labor force, communication with community, and director' role of public health center in the community as core competencies by in-depth interview. The skill - knowledge-attitude competencies were highest in order in the survey for placing priority (by Borich score) of 29 core competencies. In design stage, the educational objective of curriculum was established, that is to develop the competencies of knowledge, skills, and attitude needed for physician of public health in 21th century. In development and implementation stage, it is important to decide to lecturer, to get in advance educational materials to do the maintenance and management of curriculum. In the stage of evaluation, the educational satisfaction was high on the whole and educational effect was statistically significant. Conclusions: This study was an initial study of Korean doctors, and it aims to pursue competency-based education as a continuing professional development (CPD) beyond continuing medical education (CME) including knowledge, skills, and attitudes.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.92-104
• /
• 2021

This study aims to analyze online news articles to identify social issues related to patient safety and compare the changes in these issues before and after the implementation of the Patient Safety Act. This study performed text mining through the R program, wherein 7,600 online news articles were collected from January 1, 2010, to March 5, 2020, and examined using keyword analysis, topic modeling, and word co-occurrence network analysis. A total of 2,609 keywords were categorized into 8 topics: "medical practice", "medical personnel", "infection and facilities", "comprehensive nursing service", "medicine and medical supplies", "system development and establishment for improvement", "Patient Safety Act" and "healthcare accreditation". The study revealed that keywords such as "patient safety awareness", "infection control" and "healthcare accreditation" appeared before the implementation of the Patient Safety Act. Meanwhile, keywords such as "patient safety culture". and "administration and injection" appeared after the act's implementation with improved ranking of importance pertaining to nursing-related terminology. Interest in patient safety has increased in the medical community as well as among the public. In particular, nursing plays an important role in improving patient safety. Therefore, the recognition of patient safety as a core competency of nursing and the persistent education of the public are vital and inevitable.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.1
• /
• pp.21-30
• /
• 2022

Objectives: The purpose of this study is to suggest an optimal method by comparing the analysis methods of work environment measurement datasets including left-censored data where one or more measurements are below the limit of detection (LOD). Methods: A computer program was used to generate left-censored datasets for various combinations of censoring rate (1% to 90%) and sample size (30 to 300). For the analysis of the censored data, the simple substitution method (LOD/2), β-substitution method, maximum likelihood estimation (MLE) method, Bayesian method, and regression on order statistics (ROS)were all compared. Each method was used to estimate four parameters of the log-normal distribution: (1) geometric mean (GM), (2) geometric standard deviation (GSD), (3) 95th percentile (X95), and (4) arithmetic mean (AM) for the censored dataset. The performance of each method was evaluated using relative bias and relative root mean squared error (rMSE). Results: In the case of the largest sample size (n=300), when the censoring rate was less than 40%, the relative bias and rMSE were small for all five methods. When the censoring rate was large (70%, 90%), the simple substitution method was inappropriate because the relative bias was the largest, regardless of the sample size. When the sample size was small and the censoring rate was large, the Bayesian method, the β-substitution method, and the MLE method showed the smallest relative bias. Conclusions: The accuracy and precision of all methods tended to increase as the sample size was larger and the censoring rate was smaller. The simple substitution method was inappropriate when the censoring rate was high, and the β-substitution method, MLE method, and Bayesian method can be widely applied.

• The Journal of KAIRB
• /
• v.4 no.1
• /
• pp.16-22
• /
• 2022

Purpose: The traditional ethical study only suggests a blurred insight on the research using medical big data, especially in this rapid-changing and demanding environment which is called "4th Industry Revolution." Current institutional/ethical issues in big data research need to approach with the thoughtful insight of past ethical study reflecting the understanding of present conditions of this study. This study aims to examine the ethical issues that are emerging in recent health care big data research. So, this study aims to survey the public perceptions on of health care big data as part of the process of public discourse and the acceptance of the utility and provision of big data research as a subject of health care information. In addition, the emerging ethical challenges and how to comply with ethical principles in accordance with principles of the Belmont report will be discussed. Methods: Survey was conducted from June 3th August to 6th September 2020. The online survey was conducted through voluntary participation through Internet users. A total of 319 people who completed the survey (±5.49%P [95% confidence level] were analyzed. Results: In the area of the public's perspective, the survey showed that the medical information is useful for new medical development, but it is also necessary to obtain consents from subjects in order to use that medical information for various research purposes. In addition, many people were more concerned about the possibility of re-identifying personal information in medical big data. Therefore, they mentioned the necessity of transparency and privacy protection in the use of medical information. Conclusion: Big data on medical care is a core resource for the development of medicine directly related to human life, and it is necessary to open up medical data in order to realize the public good. But the ethical principles should not be overlooked. The right to self-determination must be guaranteed by means of clear, diverse consent or withdrawal of subjects, and processed in a lawful, fair and transparent manner in the processing of personal information. In addition, scientific and ethical validity of medical big data research is indispensable. Such ethical healthcare data is the only key that will lead to innovation in the future.