• IMMUNE NETWORK
• /
• v.11 no.1
• /
• pp.11-41
• /
• 2011

The discovery of microRNA (miRNA) is one of the major scientific breakthroughs in recent years and has revolutionized current cell biology and medical science. miRNAs are small (19~25nt) noncoding RNA molecules that post-transcriptionally regulate gene expression by targeting the 3' untranslated region (3'UTR) of specific messenger RNAs (mRNAs) for degradation of translation repression. Genetic ablation of the miRNA machinery, as well as loss or degradation of certain individual miRNAs, severely compromises immune development and response, and can lead to immune disorders. Several sophisticated regulatory mechanisms are used to maintain immune homeostasis. Regulatory T (Treg) cells are essential for maintaining peripheral tolerance, preventing autoimmune diseases and limiting chronic inflammatory diseases. Recent publications have provided compelling evidence that miRNAs are highly expressed in Treg cells, that the expression of Foxp3 is controlled by miRNAs and that a range of miRNAs are involved in the regulation of immunity. A large number of studies have reported links between alterations of miRNA homeostasis and pathological conditions such as cancer, cardiovascular disease and diabetes, as well as psychiatric and neurological diseases. Although it is still unclear how miRNA controls Treg cell development and function, recent studies certainly indicate that this topic will be the subject of further research. The specific circulating miRNA species may also be useful for the diagnosis, classification, prognosis of diseases and prediction of the therapeutic response. An explosive literature has focussed on the role of miRNA. In this review, I briefly summarize the current studies about the role of miRNAs in Treg cells and in the regulation of the innate and adaptive immune response. I also review the explosive current studies about clinical application of miRNA.

• Journal of Korean society of Dental Hygiene
• /
• v.11 no.4
• /
• pp.511-522
• /
• 2011

Objectives : The purpose of this study was to provide some information on the development of oral health care programs geared toward diabetics and ways of promoting their oral health. Methods : The subjects in this study were 586 diabetics who were selected from the 2009 third-year raw data of the 4th(2007~2009) National Health & Nutrition Survey. The data were analyzed with the statistical package SPSS 12.0 to grasp the influence of their sociodemographic characteristics and oral health behaviors on the presence or absence of periodontal diseases and missing tooth. Results : 1. Periodontal diseases were twofold more prevalent among the men than the women(p<0.01). By age, those who were in their 60s had 1.11-fold more periodontal diseases than those who were in their 70s and up(p<0.05). 2. The men and women were similar to each other in the number of missing tooth. By age, the number of missing tooth got smaller in proportion to decrease in age. By income, the number of missing tooth was 1.48-fold larger among the patients who earned an income of one million won or less than those who earned an income of two million won or more(p<0.01). Conclusions : The above-mentioned findings suggest that prospective cohort studies should be implemented to present prediction models of periodontal diseases and diabetes instead of merely sticking to cross-sectional studies. And oral health programs should be developed based on the findings of cohort studies to encourage diabetics to care about their oral health, and in which way they should be helped to promote their oral health should carefully be considered.

• Journal of health informatics and statistics
• /
• v.41 no.3
• /
• pp.318-323
• /
• 2016

Objectives: Except the known risk factors for stroke, few studies have identified novel metabolic markers that could effectively detect stroke at an early stage. In this study, we explored the dose-response relationship between serum metabolites and the incidence of stroke. Methods: We studied 213 adults in the Korean Cancer Prevention Study-II (KCPS-II) biobank and estimated dose-response relationship between serum metabolites and stroke (42 cases and 171 controls). Three serum metabolites (Acetylcholine, HexadecylAcetylGlycerol, and 1-acetyl-2-formyl-sn-glycero-3-phosphocholine) were used in this study. The analysis included (1) exploratory nonlinear analysis, (2) estimation of flexion points and slopes at below and above the points. In the model to estimate risk of incidence of stroke, we controlled for conventional risk factors such as age, sex, systolic blood pressure, type 2 diabetes, triglyceride, and smoking status. Results: The relationship between incidence of stroke and log-transformed 1-acetyl-2-formyl-sn-glycero-3-phosphocholine was non-linear with flexion point around intensity score of 8.8, whereas other metabolites, log-transformed Acetylcholine and HexadecylAcetylGlycerol, showed negative linear patterns. Conclusions: The study suggests that metabolic markers are associated with incidence of stroke, particularly, at or above the flexion point. The study result may contribute to developing a novel system for precise stroke prediction.

• Journal of Korean Neurosurgical Society
• /
• v.65 no.4
• /
• pp.582-590
• /
• 2022

Objective : Hydrocephalus after intracerebral hemorrhage (ICH) is known to be related to poor prognosis and mortality. We analyzed predictors of permanent hydrocephalus in the patients with surgically treated supratentorial ICH. Methods : From 2004 to 2019, a total of 414 patients with surgically treated primary supratentorial ICH were included. We retrospectively analyzed age, sex, preexisting hypertension and diabetes, location and volume of ICH, presence and severity of intraventricular hemorrhage (IVH), and type of surgery. Results : Forty patients (9.7%) required shunt surgery. Concomitant IVH was higher in the 'shunt required' group (92.5%) than in the 'shunt not required' group (67.9%) (p=0.001). IVH severity was worse in the 'shunt required' group (13.5 vs. 7.5, p=0.008). Craniectomy (47.5%) was significantly high in the 'shunt required' group. According to multivariable analysis, the presence of an IVH was 8.1 times more frequent and craniectomy was 8.6 times more frequent in the 'shunt required' group. In the comparison between craniotomy and craniectomy group, the presence of an IVH was related with a 3.9 times higher (p=0.033) possibility and craniectomies rather than craniotomies with a 7-times higher possibility of shunt surgery (p<0.001). Within the craniectomy group, an increase in the craniectomy area by 1 cm² was correlated with a 3.2% increase in the possibility of shunt surgery (odds ratio, 1.032; 95% confidence interval, 1.005-1.061; p=0.022). Conclusion : Presence of IVH, the severity of IVH and decompressive craniectomy were related to the development of shunt dependent hydrocephalus in the patients with ICH. The increasing size of craniectomy was related with increasing rate of shunt requirement.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Chest Surgery
• /
• v.13 no.3
• /
• pp.174-185
• /
• 1980

It was my great nohour that I can be exposed to such plenty materials of the coronary bypass surgery. Here, I am summarizing the xoronary bypass surgery, clinically. The material is serial 101 patients who underwent coronary bypass surgery between July 17, 1979 to November 30, 1979 in Shadyside Hospital, University of Pittsburgh. 1. Incidence of the Atherosclerosis is frequent in white, male, fiftieth who are living in industrialized country. It has been told the etiologic factor of the atherosclerosis is hereditary, hyperlipidemia, hypertension, smoking, drinking, diabetes, obesity, stress, etc. 2. The main and most frequent complication of the coronary atherosclerosis is angina pectoris. Angina pectoris is the chief cause of coronary bypass surgery and the other causes of coronary bypass surgery are obstruction of the left main coronary artery, unstable angina, papillary muscle disruption or malfunction and ventricular aneurysm complicated by coronary artery disease. 3. The preoperative clinical laboratory examination shows abnormal elevation of plasma lipid in 82 patint, plasma glucose in 40 patient, total CPK-MB in 24 patient stotal LDH in 22 patient out of 101 patient. 4. Abnormal ECG findings in preoperative examine were 29.1% myocardial infarction, 25.8% ischemia and injury, 14.6T conduction defect. 5. Also we had done Echocardiography, Tread Mill Test, Myocardial Scanning, Vectorcardiography and Lung function test to get adjunctive benefit in prediction of prognosis and accurate diagnosis. 6. The frequency of coronary atherosclerosis in main coronary arteries were LAD, RCA and Circumflex in that order. 7. The patients' main complaints which were became as etiologic factor undergoing coronary bypass surgery were angina, dyspnea, diaphoresis, dizziness, nausea and etc. 8. For the coronary bypass surgery, we used cardiopulmonary bypass machine, non-blood, diluting prime, cold cardioplegic solution and moderate cooling for the myocardial protection. 9. We got the grafted veins from Saphenous and Cephalic vein. Reversed and anastomosed between aorta and distal coronary A. using 5-0 and 7-0 prolene continuous suture. Occasionally we used internal mammary A. as an arterial blood source and anastomosed to the distal coronary A. and to side fashion. 10. The average cardiopulmonary bypass time for every graft was 43.9 min. and aortic clamp time was 23 minute. We could Rt. coronary A. bypass surgery only by stand by the cardiopulmonary machine and in the state of pumping heart. 11. Rates by the noumbers of graft were as follow : 21.8% single, 33.7% double, 26.7% triple, 13.9% quadruple, 3% quintuple and 1% was sixtuple graft. 12. combined procedures with coronary bypass surgery were 6% aneurysmectomy, 3% AVR, 1% MVR, 13% pacer implantation and 1% intraaortic ballon setting. 13. We could see the complete abolition of anginal pain after operation in 68% of patient, improvement 25.8%, no change in 3.1%, and there was unknown in 3%. 14. There were 4% immediate postoperative deaths, 13.5% some kinds of heart complication, 51.3% lung complications 33.3% pleural complications as prognosis.

• 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.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• Sleep Medicine and Psychophysiology
• /
• v.24 no.1
• /
• pp.38-45
• /
• 2017

Objectives: Sleep disturbance is a very rapidly growing disease with aging. The purpose of this study was to investigate the prevalence of sleep disturbances and its predictive factors in a three-year cohort study of people aged 60 years and over in Korea. Methods: In 2012 and 2014, we obtained data from a survey of the Korean Social Life, Health, and Aging Project. We asked participants if they had been diagnosed with stroke, myocardial infarction, angina pectoris, arthritis, pulmonary tuberculosis, asthma, cataract, glaucoma, hepatitis B, urinary incontinence, prostate hypertrophy, cancer, osteoporosis, hypertension, diabetes, hyperlipidemia, or metabolic syndrome. Cognitive function was assessed using the Mini-Mental State Examination for dementia screening in 2012, and depression was assessed using the Center for Epidemiologic Studies Depression Scale in 2012 and 2014. In 2015, a structured clinical interview for Axis I psychiatric disorders was administered to 235 people, and sleep disturbance was assessed using the Pittsburgh Sleep Quality Index. The perceived stress scale and the State-trait Anger Expression Inventory were also administered. Logistic regression analysis was used to predict sleep disturbance by gender, age, education, depression score, number of coexisting diseases in 2012 and 2014, current anger score, and perceived stress score. Results: Twenty-seven percent of the participants had sleep disturbances. Logistic regression analysis showed that the number of medical diseases three years ago, the depression score one year ago, and the current perceived stress significantly predicted sleep disturbances. Conclusion: Comorbid medical disease three years previous and depressive symptoms evaluated one year previous were predictive of current sleep disturbances. Further studies are needed to determine whether treatment of medical disease and depressive symptoms can improve sleep disturbances.