Background: To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. Methods: Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. Results: In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. Conclusion Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.

Background: To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. Methods: Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. Results: In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. Conclusion Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.

Background: and Purpose: This study uses an artificial-intelligence model (recurrent neural network) for evaluating the following hypothesis: social determinants of disease association in a middle-aged or old population are different across gender and age groups. Here, the disease association indicates an association among cerebrovascular disease, hearing loss and cognitive impairment. Methods: Data came from the Korean Longitudinal Study of Ageing (2014–2016), with 6,060 participants aged 53 years or more, that is, 2,556 men, 3,504 women, 3,640 aged 70 years or less (70−), 2,420 aged 71 years or more (71+). The disease association was divided into 8 categories: 1 category for having no disease, 3 categories for having 1, 3 categories for having 2, and 1 category for having 3. Variable importance, the effect of a variable on model performance, was used for finding important social determinants of the disease association in a particular gender/age group, and evaluating the hypothesis above. Results: Based on variable importance from the recurrent neural network, important social determinants of the disease association were different across gender and age groups:1) leisure activity for men; 2) parents alive, income and economic activity for women; 3) children alive, education and family activity for 70−; and 4) brothers/sisters cohabiting, religious activity and leisure activity for 70+. Conclusions The findings of this study support the hypothesis, suggesting the development of new guidelines reflecting different social determinants of the disease association across gender and age groups.

The purpose of this study was to compare the accuracy of the working models fabricated by the subtractive and additive processing methods based on the 3-dimensional reconstruction model. A total of 20 models were fabricated with subtractive processing method from polymethyl methacrylate (PMMA) blocks using the stereolithography (STL) file of master gypsum model and another 20 models were fabricated with additive processing method using 3D printer with 0.025 mm of a layer thickness. The CAD-reference-model (CRM) and CAD-test-model (CTM) were superimposed by a software for accuracy analysis (Geomagic Qualify 13), where the STL files were transformed to point cloud data and the surface data (CRM and CTM) were subjected to initial alignment and followed by re-alignmented according to best-fit superimposition. The distances between surface data and all points, in this process, were converted to the root mean square (RMS) and averaged. In the experimental results, It was shown that the accuracy is higher in work model fabricated by additive processing method compared to one fabricated by subtractive one (p < 0.05). In addition, it is considered that the working model fabricated by subtractive processing method is to be clinically applicable by improving the improper reproducibility of the tooth surface and depressed area.
Calcium Sulfate ; Methods ; Polymethyl Methacrylate ; Printing, Three-Dimensional ; Tooth

PURPOSE: The purpose of this study was to evaluate the cost effectiveness of colorectal cancer screening interventions with their effects on health disparity being considered. MATERIALS AND METHODS: Markov cohort simulation was conducted with the cycle/duration of 1/40 year(s). Data came from the results of randomized trials and others. Participants were hypothetical cohorts aged 50 years as of year 2013 in 16 Korean provinces. The interventions until the age of 80 were annual organized fecal occult blood test (FOBT) (standard screening), annual FOBT with basic reminders for provinces with higher mortalities than the national average (targeted reminder) and annual FOBT with basic/enhanced reminders for all provinces (universal reminder 1 and 2). The comparison was non-screening, the outcome was quality-adjusted life years, and only medical costs for screening and treatment were considered from a societal perspective. The Atkinson incremental cost effectiveness ratio (Atkinson ICER), the incremental cost effectiveness ratio adjusted by the Atkinson Inequality Index, was used to evaluate the cost effectiveness of the four interventions with their impacts on regional health disparity being considered. RESULTS: Health disparity was smallest (or greatest) in non-screening (or the standard screening). The targeted reminder had smaller health disparity, and smaller Atkinson ICER with respect to standard screening, than did the universal reminder 1 and 2. CONCLUSION: The targeted reminder might be more cost effective than the universal reminders with their effects on health disparity being considered. This study helps to develop promotional effort for colorectal cancer screening with both the greatest cost effectiveness and the smallest health disparity.
Cohort Studies ; Colorectal Neoplasms* ; Cost-Benefit Analysis* ; Health Status Disparities ; Mass Screening* ; Mortality ; Occult Blood ; Quality-Adjusted Life Years ; Socioeconomic Factors

OBJECTIVES: The purpose of this study was to investigate the association between suicidal behavior and patterns of alcohol consumption in Korean adults. METHODS: This study was based on data provided by the Korea National Health and Nutritional Examination Survey from 2007 to 2011. A total of 42 347 subjects were included in the study, of whom 19 292 were male and 23 055 were female. Logistic regression analysis was performed to assess the association between patterns of alcohol consumption and suicidal behavior. RESULTS: Among the study subjects, 1426 males (11.3%) and 3599 females (21.2%) had experienced suicidal ideation, and 106 males (0.8%) and 190 females (1.1%) had attempted suicide during the previous 12 months. Alcohol Use Disorders Identification Test (AUDIT) scores were found to be associated with suicidal ideation in males and associated with both suicidal ideation and suicide attempts in females. Alcoholic blackouts were associated with suicidal ideation and suicide attempts in males, and were also associated with suicidal ideation in females. CONCLUSIONS: In this study, we found that certain patterns of alcohol consumption were associated with suicidal behaviors. In particular, only alcoholic blackouts and categorized AUDIT scores were found to be associated with suicidal behavior in males. We therefore suggest that further research is needed to examine this relationship prospectively and in other settings.
Adult ; Aged ; Alcohol Drinking/*psychology ; Alcohol-Related Disorders/pathology ; Asian Continental Ancestry Group ; Demography ; Female ; Humans ; Logistic Models ; Male ; Middle Aged ; Nutrition Surveys ; Republic of Korea ; Sex Factors ; Suicidal Ideation ; Suicide, Attempted/*psychology/statistics & numerical data

PURPOSE: The aim of study was to provide suggestions for prioritizing research in effort to reduce cancer burden in Korea based on a comprehensive analysis of cancer burden and Delphi consensus among cancer experts. MATERIALS AND METHODS: Twenty research plans covering 10 topics were selected based on an assessment of the literature, and e-mail surveys were analyzed using a two-round modified Delphi method. Thirty-four out of 79 experts were selected from four organizations to participate in round one, and 21 experts among them had completed round two. Each item had two questions; one regarding the agreement of the topic as a priority item to reduce cancer burden, and the other about the importance of the item on a nine-point scale. A consensus was defined to be an average lower coefficient of variation with less than 30% in importance. RESULTS: Seven plans that satisfied the three criteria were selected as priority research plans for reducing cancer burden. These plans are "research into advanced clinical guidelines for thyroid cancer given the current issue with over-diagnosis," "research into smoking management plans through price and non-price cigarette policy initiatives," "research into ways to measure the quality of cancer care," "research on policy development to expand hospice care," "research into the spread and management of Helicobacter pylori," "research on palliative care in a clinical setting," and "research into alternative mammography methods to increase the accuracy of breast cancer screenings." CONCLUSION: The seven plans identified in this study should be prioritized to reduce the burden of cancer in Korea. We suggest that policy makers and administrators study and invest significant effort in these plans.
Administrative Personnel ; Breast Neoplasms ; Consensus ; Delphi Technique ; Early Detection of Cancer ; Electronic Mail ; Health Policy* ; Helicobacter ; Helicobacter pylori ; Hospices ; Humans ; Korea ; Mammography ; Palliative Care ; Policy Making ; Smoke ; Smoking ; Thyroid Neoplasms ; Tobacco Products

PURPOSE: This study estimated the economic burden of cancer in Korea during 2000-2010 by cancer site, gender, age group, and cost component. MATERIALS AND METHODS: Data came from national health insurance claims data and information from Statistics Korea. Based on the cost of illness method, this study calculated direct, morbidity and mortality cost of cancer in the nation during 2000-2010 by cancer site, gender, and age group. RESULTS: With an average annual growth rate of 8.9%, the economic burden of cancer in Korea increased from 11,424 to 20,858 million US$ (current US dollars) during 2000-2010. Colorectal, thyroid, and breast cancers became more significant during the period, i.e., the 5th/837, the 11th/257, and the 7th/529 in 2000 to the 3rd/2,210, the 5th/1,724, and the 6th/1,659 in 2010, respectively (rank/amount in million US$ for the total population). In addition, liver and stomach cancers were prominent during the period in terms of the same measures, i.e., the 1st/2,065 and the 2nd/2,036 in 2000 to the 1st/3,114 and the 2nd/3,046 in 2010, respectively. Finally, the share of mortality cost in the total burden dropped from 71% to 51% in Korea during 2000-2010, led by colorectal, thyroid, breast, and prostate cancers during the period. These results show that the economic burden of cancer in Korea is characterized by an increasing importance of chronic components. CONCLUSION: Incorporation of distinctive epidemiological, sociocultural contexts into Korea's cancer control program, with greater emphasis on primary prevention such as sodium-controlled diet and hepatitis B vaccination, may be needed.
Aging ; Breast ; Cost of Illness ; Diet ; Hepatitis B ; Humans ; Incidence ; Korea ; Liver ; Mortality ; National Health Programs ; Primary Prevention ; Prostatic Neoplasms ; Stomach Neoplasms ; Thyroid Gland ; Vaccination

OBJECTIVES: To comprehensively examine the relationship between current sleep duration and past suicidal idea or attempt among Korean adolescents. METHODS: Data came from the 2009 Korea Youth Risk Behavior Web-based Survey with 75 066 participants (with the participation rate of 97.6%) in 800 middle and high schools. Binary logistic regression was conducted by gender and depressed mood to identify significant factors for suicidal ideation/attempt. The dependent variable was the log odds of suicidal ideation/attempt, while the independent/control variables were sleep duration and other demographic, socio-economic and health-related factors. RESULTS: A negative association between sleep duration and suicidal ideation or attempt was weaker for those with depressed mood than for those without such experience in Korea for Year 2009. The odds ratio of suicidal ideation/attempt regarding less than 4 hours of sleep compared to 6 to 7 hours of sleep, was smaller in a group with depressed mood than in a group without such experience, for example, 1.64 (95% confidence interval [CI], 1.29 to 2.08) vs. 2.06 (95% CI, 1.34 to 3.17) for men's suicidal ideation, 2.50 (95% CI, 1.69 to 3.69) vs. 3.89 (95% CI, 1.74 to 8.66) for men's suicidal attempt. A negative association between age (or self-rated health) and suicidal ideation/attempt was also weaker for those with depressed mood than for those without such experience in the nation for the year. CONCLUSIONS: There was a negative association between sleep duration and suicidal ideation/attempt in Korea for Year 2009 and this association was weaker for those with depressed mood than for those without such experience. Based on the findings of this study, adolescents' better mental health and longer, more comfortable sleep might help to prevent their suicidal ideation and attempt in Korea.
Adolescent ; Demography ; Female ; Humans ; Internet ; Logistic Models ; Male ; Odds Ratio ; Republic of Korea ; Sex Factors ; *Sleep ; Socioeconomic Factors ; *Suicidal Ideation ; Suicide, Attempted/statistics & numerical data ; Time Factors ; User-Computer Interface

This study renewed the estimation of disability weights for cancers in Korea, reflecting the nation's economic and medical-technological development during the past 10 yr. Thirty-two medical doctors evaluated disability weights for 24 major cancers based on the visual analogue scale (VAS) method. To check the intra-rater reliability, a correlation was calculated between 2011 and 2012 medians. To assess the inter-rater reliability, a correlation was estimated between oncologist and non-oncologist medians. To assess the inter-method reliability, a correlation was calculated between medians on VAS and Person-Trade-Off approaches. Moreover, findings in this study were compared to those in 2003 research. Spearman correlation was used and the 1% significance level was applied. Disability weights were relatively high for pancreas cancer (0.90), gallbladder cancer (0.81), mouth and oropharynx cancer (0.80), and esophagus cancer (0.80). Conversely, they were relatively low for breast cancer (0.37), prostate cancer (0.33) and thyroid cancer (0.10). All the inter-rater reliabilities were higher than 0.7. Indeed, the intra-rater and inter-method reliabilities were 0.752 and 0.927, respectively. Above all, disability weights for major cancers went down in Korea during 2003-2012, reflecting the progress of medical technology and the growth of cancer survival.
Cost of Illness ; *Disability Evaluation ; Humans ; Neoplasms/economics/*physiopathology ; Republic of Korea