• Title/Summary/Keyword: binary analysis

Search Result 1,399, Processing Time 0.031 seconds

The Effect of Social Isolation on Dementia in rural elderly: Comparison Between Young-old and Old-old Group (농촌 노인의 사회적 고립이 치매에 미치는 영향 : 전기노인과 후기노인 비교 분석)

  • Lee, Sangchul
    • Korean Journal of Social Welfare Studies
    • /
    • v.48 no.2
    • /
    • pp.143-171
    • /
    • 2017
  • Along with the well-established evidence on the negative effect of social isolation on physical mental health and mortality, increasing attention has been paid to multi-dimensional nature of social isolation. In this study, the main effect and interaction effect of objective and subjective social isolation on heterogeneous age cohort related to the onset of dementia, which is becoming a social problem due to rapid aging of health issues, was examined through binary logistic regression analysis. Data came from the first wave of Korean Social Life, Health and Aging Project (KSHAP) (N= 814). Findings showed 1) in the young-old, objective isolation was a significant on the incidence of dementia, 2) in the old-old, subjective isolation increased the risk of dementia. In summary, the relative influence of objective and subjective social isolation related to the incidence of dementia varies depending on the young-old and old-old. On the other hand, the interaction effect of objective and subjective social isolation on dementia was not significant in both the young-old and old-old. Based on the findings, we discussed implications and suggestions for future research and relevant policy and program development(dementia-friendly communities) for ameliorating objective and subjective social isolation.

Risk Factors for Depression of Patients with Tuberculosis in Tuberculosis Specialty Hospital (결핵전문병원에 입원한 결핵환자의 우울증위험인자)

  • Wang, Jung-Hyun;Park, Chul-Soo;Kim, Bong-Jo;Lee, Cheol-Soon;Cha, Boseok;Lee, So-Jin;Lee, Dongyun;Seo, Ji-Yeong;Ahn, InYoung;Baek, Jong Chul;Kang, Hyung Seok;Moon, Sung Ho
    • Korean Journal of Psychosomatic Medicine
    • /
    • v.23 no.2
    • /
    • pp.114-120
    • /
    • 2015
  • Objectives : This study aimed to investigate the risk factors of depression for patients with tuberculosis(TB). Methods : A total of 57 patients with TB were recruited. All participants completed the Becks Depression Inventory-II for evaluating depressive symptoms. The risk factor for depression was analyzed by binary logistic regression analysis. Nomogram was performed for probability of depression. Results : Low body mass index(BMI, OR 0.801, 95% CI 0.65, 0.98), interruption of treatment for TB(OR 5.908, 95% CI 1.19, 29.41), past history of depression(OR 24.653, 95% CI 1.99, 308.44) were associated with increased risk for depression. The calibration curve for predicting probability of survival showed a good agreement between the nomogram and actual observation(Original C-index=0.789, bias corrected C-index=0.754). Conclusions : The result of the present study indicate that low BMI, interruption of treatment for TB, and past history of depression were risk factors for depression in patients with TB. The psychiatric intervention may be needed to prevent depression if the patients with TB have risk factor during treatment for TB.

A Study on the Methodology of Early Diagnosis of Dementia Based on AI (Artificial Intelligence) (인공지능(AI) 기반 치매 조기진단 방법론에 관한 연구)

  • Oh, Sung Hoon;Jeon, Young Jun;Kwon, Young Woo;Jeong, Seok Chan
    • The Journal of Bigdata
    • /
    • v.6 no.1
    • /
    • pp.37-49
    • /
    • 2021
  • The number of dementia patients in Korea is estimated to be over 800,000, and the severity of dementia is becoming a social problem. However, no treatment or drug has yet been developed to cure dementia worldwide. The number of dementia patients is expected to increase further due to the rapid aging of the population. Currently, early detection of dementia and delaying the course of dementia symptoms is the best alternative. This study presented a methodology for early diagnosis of dementia by measuring and analyzing amyloid plaques. This vital protein can most clearly and early diagnose dementia in the retina through AI-based image analysis. We performed binary classification and multi-classification learning based on CNN on retina data. We also developed a deep learning algorithm that can diagnose dementia early based on pre-processed retinal data. Accuracy and recall of the deep learning model were verified, and as a result of the verification, and derived results that satisfy both recall and accuracy. In the future, we plan to continue the study based on clinical data of actual dementia patients, and the results of this study are expected to solve the dementia problem.

The Fate of Proximal Junctional Vertebral Fractures after Long-Segment Spinal Fixation : Are There Predictable Radiologic Characteristics for Revision surgery?

  • Jang, Hyun Jun;Park, Jeong Yoon;Kuh, Sung Uk;Chin, Dong Kyu;Kim, Keun Su;Cho, Yong Eun;Hahn, Bang Sang;Kim, Kyung Hyun
    • Journal of Korean Neurosurgical Society
    • /
    • v.64 no.3
    • /
    • pp.437-446
    • /
    • 2021
  • Objective : To investigate the radiographic characteristics of the uppermost instrumented vertebrae (UIV) and UIV+1 compression fractures that are predictive of revision surgery following long-segment spinal fixation. Methods : A total 27 patients who presented newly developed compression fracture at UIV, UIV+1 after long segment spinal fixation (minimum 5 vertebral bodies, lowest instrumented vertebra of L5 or distal) were reviewed retrospectively. Patients were divided into two groups according to following management : revisional surgery (group A, n=13) and conservative care (group B, n=14). Pre- and postoperative images, and images taken shortly before and after the occurrence of fracture were evaluated for radiologic characteristics Results : Despite similar degrees of surgical correction of deformity, the fate of the two groups with proximal junctional compression fractures differed. Immediately after the fracture, the decrement of adjacent disc height in group A (32.3±7.6 mm to 23.7±8.4 mm, Δ=8.5±6.9 mm) was greater than group B (31.0±13.9 mm to 30.1±15.5 mm, Δ=0.9±2.9 mm, p=0.003). Pre-operative magnetic resonance imaging indicated that group A patients have a higher grade of disc degeneration adjacent to fractured vertebrae compared to group B (modified Pfirrmann grade, group A : 6.10±0.99, group B : 4.08±0.90, p=0.004). Binary logistic regression analysis indicated that decrement of disc height was the only associated risk factor for future revision surgery (odds ratio, 1.891; 95% confidence interval, 1.121-3.190; p=0.017). Conclusion : Proximal junctional vertebral compression fractures with greater early-stage decrement of adjacent disc height were associated with increased risk of future neurological deterioration and necessity of revision. The condition of adjacent disc degeneration should be considered regarding severity and revision rate of proximal junctional kyphosis/proximal junction failures.

A Convergence Study on association of Internet Use Time with Perceived Status in Adolescents (청소년 인터넷 사용시간이 청소년 주관적 상태에 미치는 영향에 대한 융합연구)

  • Baek, Seung Hee;Kim, Ji hyun
    • Journal of the Korea Convergence Society
    • /
    • v.9 no.11
    • /
    • pp.153-159
    • /
    • 2018
  • The purpose of this study is to grasp the internet use time that young people use for purposes other than learning purpose, to grasp the perceived status of the youth according to internet use time and to grasp the interrelationships of them. Using the 2016 youth health behavior online survey, the odds ratios and 95% confidence intervals of perceived status according to internet use time were calculated by binary logistic regression analysis. The main results are as follows. In perceived health and perceived oral health the odds ratios of perceived who feel that they are perceived and unhealthy as the time spent using the Internet increased significantly compared to those who did not use the Internet for learning purposes. In the perceived body type, the odds ratio of being overweight increased significantly with longer internet use time. The odds ratios of perceived happiness were 1.19 times (CI = 1.10-1.30) higher than the perceived expectation of unhappiness when using the Internet for over 300 minutes. The use of the internet for a long time other than the purpose of learning may have a negative effect on the health and happiness of the youth, so we think that the recommended time for using the internet is necessary.

Binary classification of bolts with anti-loosening coating using transfer learning-based CNN (전이학습 기반 CNN을 통한 풀림 방지 코팅 볼트 이진 분류에 관한 연구)

  • Noh, Eunsol;Yi, Sarang;Hong, Seokmoo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.2
    • /
    • pp.651-658
    • /
    • 2021
  • Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

Determinants of Attitude toward the Electronic Wristband System to Tackle the Spread of COVID-19 -Focused on the Interaction between Class and Age- (코로나19 자가격리 안심밴드에 대한 태도 결정 요인 -계층과 연령의 상호작용을 중심으로-)

  • Lee, Jae-Wan
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.6
    • /
    • pp.285-294
    • /
    • 2021
  • This study analyzes the factors that determine the attitude toward the electronic wristband(smartband) to check the position of self-quarantine subjects due to COVID-19. Furthermore, I analyze the interaction of class and age among the factors that determine attitudes toward the electronic wristband. In this study, the attitude toward self-quarantine electronic wristband is analyzed as a binary logit model, focusing on class and age. As a result of the analysis, the middle class significantly agreed with the self-quarantine electronic wristband compared to the lower class, and the older the person, the more in favor. On the other hand, the interaction between the class and the age shows that the age weakens the positive effect on the attitude of the self-quarantine electronic wristband in the middle and upper middle classes. The implication of this study is that it is necessary to push for mandatory electronic wristband in areas with high proportion of high-aged people with positive attitude toward self-quarantine electronic wristband and in the same age group, the approval rate is low, so it is necessary to promote mandatory electronic wristband in areas where the vulnerable class is dense.

The Estimation of the Demand of Newly Married Couples for Public Rental Housing in Chungnam (충남 신혼부부의 공공임대주택 수요 추정과 정책적 함의)

  • Hong, Sung-Hyo;Im, Jun-Hong
    • Land and Housing Review
    • /
    • v.13 no.1
    • /
    • pp.11-22
    • /
    • 2022
  • This paper estimates the demand of newly married couples for public rental housing in Chungnam. This research attempts to overcome data limitations by linking survey data with administrative data for analysis. First, the results of a binary logit model that analyzes newly married couples' intention to move into public rental housing, based on the Chungnam Social Survey 2019, reveal that residential location, educational level, housing type, and tenure type have a statistically significant effect. By combining the estimated coefficients with another dataset, the statistics of newly married couples for administration purposes acquired from Statistics Korea, this research estimates the demand for public rental housing among the newly married couples in Chungnam. The estimation results show that the total demand for public rental housing in Chungnam is 11,424 units among 43,705 newly married couples. The total demand of 21,685 newly married couples who occupy rental housing is estimated to be 9,436 units. The policy for providing public rental housing to newly married couples in Chungnam aims to increase their fertility rates. Hence, further research should be followed up to evaluate the effect of the supply of public rental housing on fertility rates. Also, a research method should be developed to control for possible endogeneity between the demand for public rental housing and childbirths.

Comparing the Effects of Regional Household Expenditure Burden on Childbirth Intention of Married Women: The Case of Capital and Non-Capital Regions (지역별 가계지출 부담이 기혼여성의 출산 의사에 미치는 영향: 수도권과 비수도권 비교를 중심으로)

  • Lee, Da-Eun;Seo, Wonseok
    • Journal of Cadastre & Land InformatiX
    • /
    • v.51 no.2
    • /
    • pp.151-168
    • /
    • 2021
  • This study compared and analyzed the effect of the burden of household expenditure in the metropolitan and non-metropolitan areas on the intention to childbirth intention to married women using a panel logit model. To this end, this analysis targeted married women aged 25 to 39 who are highly likely to be fertile. The main results are as follows; First of all, it was confirmed that the economic power of spouse can be an important factor in the childbirth intention regardless of region. Second, it was found that the higher the satisfaction of marriage had a positive effect on the childbirth intention, and also higher the value that children must have, the higher the childbirth intention. Third, it was confirmed that the burden of household expenditure is the most important factor in the willingness to childbirth intention, excluding factors such as the number of existing children. In particular, the burden on education spending in both the capital region and non-capital region was found to be a key reason for the decrease in the childbirth intention. Lastly, the burden of household expenditure showed different effects on childbirth intention on depending on the region. Specifically, in the capital region, medical spending and loans had a greater impact, while, in the non-capital region, transportation and communication costs had a greater impact on childbirth intentions. Through the results, this study confirmed the implication that easing the burden on household expenditure is continuously necessary to enhance childbirth, and that discriminatory policy approaches are required depending on the area of residence.

The Incidence and risk factors of delirium in elderly surgical patients (외과계 병동 노인 수술 환자의 섬망 발생률과 위험요인)

  • Lee, Eun Ju;Jang, Mi;Kim, Myung Hwa;Yun, Hye Jun;Kim, Eun Mi;Chung, Young In;Kim, Bo Kyung;Im, Eun Su;Hong, Kyoung Soon
    • Journal of Korean Clinical Nursing Research
    • /
    • v.28 no.2
    • /
    • pp.137-145
    • /
    • 2022
  • Purpose: This retrospective chart review study was conducted to examine the frequency of delirium and to identify the risk factors of delirium in elderly surgical patients. Methods: The subjects of this study were 394 patients aged 65 years or older who underwent surgery. The diagnosis of delirium was based on the nursing assessment records with scores from the day of surgery to the 4th day after surgery. The collected data were analyzed by binary logistic regression analysis. Results: The incidence of delirium was 4.3%, and delirium occurred most frequently on the first day of surgery and lasted for 2.16 days on average. Of delirium patients, 76.5% underwent gastrointestinal surgery, and the most common delirium pattern was disorientation. In terms of the characteristics of the subjects, the occurrence of delirium was statistically different by age (𝝌2=10.79, p=.005), systemic-specific disease (𝝌2=9.63, p=.047), use of delirium-inducing drug(benzodiazepine) before surgery (𝝌2=15.90, p<.001), walking ability before surgery (𝝌2=7.65, p=.006), history of delirium (𝝌2=35.92, p<.001), and emergency surgery (𝝌2=16.40, p<.001). As risk factors of delirium, gastrointestinal surgery was found to increase the risk of delirium by 12.57 times (95% CI=2.45~64.46, p=.002), and the use of benzodiazepines before surgery was shown to increase delirium by 10.07 times (95% CI=2.21~45.87, p=.003). Conclusion: It is necessary for nurses to actively evaluate delirium using screening tools for early detection and prevention of delirium in elderly surgical patients with delirium risk factors.