• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.175-177
• /
• 2003

This paper addresses a problem of classifying human breast cancer into its subtypes. A main ingredient in our approach is kernel machines such as support vector machine (SVM). kernel principal component analysis (KPCA). and kernel partial least squares (KPLS). In the task of breast cancer classification, we employ both SVM and KPLS and compare their results. In addition to this classification. we also analyze the patterns of clinical outcomes in the feature space. In order to visualize the clinical outcomes in low-dimensional space, both KPCA and KPLS are used. It turns out that these methods are useful to identify correlations between clinical outcomes and the nonlinearly protected expression profiles in low-dimensional feature space.

• Biomedical Science Letters
• /
• v.20 no.4
• /
• pp.185-193
• /
• 2014

Cancers are based upon an array of orchestrated genetic changes and the identification of changes causally related to the carcinogenic process. To elucidate the mechanism of cancer carcinogenesis, it is necessary to reconstruct these molecular events at each level. Microarray technologies have been extensively used to evaluate genetic alterations associated with cancer onset and progression in clinical oncology. The clinical impact of the genomic alterations identified by microarray technologies are growing rapidly and array analysis has been evolving into a diagnostic tool to better identify high-risk patients and predict patient outcomes from their genomic profiles. Here, we discuss the state-of-the-art microarray technologies and their applications in clinical oncology, and describe the potential benefits of these analysis in the clinical implications and biological insights of cancer biology.

• Journal of Korean Clinical Nursing Research
• /
• v.23 no.1
• /
• pp.1-8
• /
• 2017

Purpose: The purpose of this study was to provide basic data required to improve nursing resources management and nurse organizations. Methods: The data were collected using a questionnaire. Participants were 294 nurses who were working at 8 hospitals with more than 500 beds located in G and C cities, Korea. Data analysis was done using t-test, ANOVA, $Scheff{\acute{e}}$ test, Pearson correlation coefficient and stepwise multiple regression analysis with SPSS. Results: There were significant correlations between self-leadership, clinical competence, job satisfaction and job involvement. Factors affecting job involvement were job satisfaction, self-leadership, length of clinical career and length of career in current department. Job satisfaction was the most influential factor with an explanatory power of 41%. Conclusion: Findings show that to strengthen job involvement, identification and management of factors that affect job satisfaction and self-leadership are required and relevant training and strategies should be developed and used.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.19
• /
• pp.8429-8433
• /
• 2014

Circulating tumor cells (CTCs) are believed to be particularly important and a reliable marker of malignancy. However, the prognostic significance of CTCs detected in patients with small cell lung cancer (SCLC) is still unclear. We therefore aimed to assess the prognostic relevance of CTCs using a meta-analysis. We searched PubMed for relevant studies and statistical analyses were conducted to calculate the hazard ratio (HR) and 95% confidence intervals (CIs) using fixed or random-effect models according to the heterogeneity of included studies. A total of 7 papers covering 440 SCLC patients were combined in the final analysis. The meta-analysis revealed that CTCs were significantly associated with shorter overall survival (HR=1.9; 95%CI: 1.19-3.04; Z=2.67; P<0.0001) and progression-free survival (HR=2.6; 95%CI: 1.9-3.54; Z=6.04; P<0.0001). The results thus suggest that the presence of CTCs indicates a poor prognosis in patients with SCLC. Further well-designed prospective studies are required to explore the clinical applications of CTCs in SCLC.

• Journal of Pharmaceutical Investigation
• /
• v.40 no.4
• /
• pp.225-230
• /
• 2010

The particulate contamination of intravenously administered fluid has been of major concern. One of the most common complications associated with long term i.v. therapy is post-infusion phlebitis (PIP). We undertook a systematic review and meta-analysis of the effect of inline filters on PIP. An electronic search of Medline, KoreaMed, and KRIST was conducted to identify randomized controlled trials evaluating the effect of inline filters. Meta-analysis was undertaken using STATA 10. A total of 62 literatures were retrieved, of which 7 were included in meta-analysis. Inline filtration for intravenous infusion significantly reduced by 39% of the incidence of phlebitis, with a relative risk of 0.61 (95% CI 0.41-0.90, p=0.012). Therefore, inline filtration is a highly effective means of decreasing the incidence of infusion phlebitis and should be considered as a part of intravenous therapy.

• Korean Journal of Occupational Health Nursing
• /
• v.14 no.1
• /
• pp.71-82
• /
• 2005

Purpose: This study analyzed domestic articles that studied job-stress of nurses using Meta Analysis to evaluate the responses resulted from job-stress and the factors affecting them. Method: To conduct this study, data were collected primarily from database of "richis" and additionally from 8 nursing journals and 5 theses for a degree on job-stress of clinical nurses. Result: As a result of Meta Analysis casual factor of job-stress, the result represented that two reasons; personal factor was the age, occupational factor were ward, duration of employment and position. By the result of analysis of effect of job-stress, satisfaction of the job, exhaustion, health status and immersion of the job were strongly related to job-stress. According to the general solution against job-stress that referred from job-stress related theses, there are several; Imagination Therapy, Assertive Training and Value Clarification Training could bring significant result. Conclusion: This study showed that because job-stress of clinical nurses had nothing to do with personal factors, job-stress management plans for nurses are needed to focus on occupational factors. Also the study suggested that various coping skills that proved to be effective are needed to be used to relieve job-stress and that's responses on nurses.

• The Journal of Information Systems
• /
• v.32 no.3
• /
• pp.41-61
• /
• 2023

Purpose This study aims to categorize the types of health, analyze the effects among health types based on network analysis find the most important type of health, and explain whether the results between health types vary depending on demographic characteristics. Design/methodology/approach This study investigated individual physical, clinical, mental, and social health(social capital and social support) levels through a survey of 100 people. Network analysis was applied to the survey data to confirm the degree centrality of nodes. Furthemore, we investigated the differences in core nodes according to gender and age groups. Findings According to the analysis result, social support was the most important health type in the entire group. Furthermore, the importance of health type was different depending on the characteristics of the groups. In the case of men, clinical health was the most important health type, and social support was analyzed to be the most important for women. In the case of young people, clinical health was the most important health type, and mental health was the most important health type in the middle-aged.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.661-674
• /
• 2021

Edwardsiellosis is difficult to treat in cultured olive flounder, Paralichthys olivaceus. It is present in the fish for a long period during all growth stages, and it often leads to mass mortalites. In this paper, the clinical patterns of Edwardsiellosis were analyzed by dividing the data into the whole-water temperature, low-water temperature, low-high water temperature, high-water temperature, and high-low water temperature groups based on various clinical signs of diseased cultured olive flounder using a decision tree technique. In the clinical sign patterns in the decision trees analyzed in the experiment, clinical signs in the liver, such as liver nodules, liver hemorrhages, and liver degeneration, were selected as the criteria for determining Edwardsiellosis. The selected clinical signs were known as the major clinical signs of Edwardsiellosis, and through consultation with fishery disease experts, the analysis confirmed that the clinical signs of Edwardsiellosis were successfully found in this study.

• The Journal of Internal Korean Medicine
• /
• v.45 no.1
• /
• pp.1-10
• /
• 2024

Objectives: This study investigated the pattern identification (PI) and clinical index of Parkinson's disease (PD) for personalized diagnosis and treatment. Methods: This prospective observational multi-center study recruited 100 patients diagnosed with PD from two Korean medicine hospitals. To cluster new subtypes of PD, items on a PI questionnaire (heat and cold, deficiency and excess, visceral PI) were evaluated along with pulse and tongue analysis. Gait analysis was performed and blood and feces molecular signature changes were assessed to explore biomarkers for new subtypes. In addition, unified PD rating scale II and III scores and the European quality of life 5-dimension questionnaire were assessed. Results: The clinical index obtained in this study analyzed the frequency statistics and hierarchical clustering analysis to classify new subtypes based on PI. Moreover, the biomarkers and current status of herbal medicine treatment were analyzed using the new subtypes. The results provide comprehensive data to investigate new subtypes and subtype-based biomarkers for the personalized diagnosis and treatment of PD patients. Ethical approval was obtained from the medical ethics committees of the two Korean medicine hospitals. All amendments to the research protocol were submitted and approved. Conclusions: An objective and standardized diagnostic tool is needed for the personalized treatment of PD by traditional Korean medicine. Therefore, we developed a clinical index as the basis for the PI clinical evaluation of PD. Trial Registration: This trial is registered with the Clinical Research Information Service (CRIS) (KCT0008677)