• 통합자연과학논문집
• /
• 제8권4호
• /
• pp.305-312
• /
• 2015

The present study showed WHtR to be significantly better than BMI and WC for prediction of metabolic-related diseases in the middle-aged and older people in Korea, based on Bayesian ordered probit model analysis. The variations of WC, BMI and WHtR were compared according to the number of metabolic-related diseases such as hypertension, dyslipidemia, stroke, myocardial infarction, angina pectoris and diabetes. It was found that the three measures showed the similar variation except a very few extreme cases for age less than 40. For subjects over the age of 40, WC was not significant and WHtR gave more influence in greater variability than BMI on the number of metabolic diseases. Also, the rate of change for WHtR was higher than for BMI as the number of metabolic-related diseases increased. Specifically, the difference of the marginal effect of WHtR between no disease and only one disease was 1.81 times higher than that of BMI. Moreover, it was pointed out that the threshold value of WHtR for obesity should be considered differently by age.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권1호
• /
• pp.97-101
• /
• 2012

Objective: With the background of aging population in China and advances in clinical medicine, the amount of operations on old patients increases correspondingly, which imposes increasing challenges to critical care medicine and geriatrics. The study was designed to describe information on the length of ICU stay from a single institution experience of old critically ill gastric cancer patients after surgery and the framework of incorporating data-mining techniques into the prediction. Methods: A retrospective design was adopted to collect the consecutive data about patients aged 60 or over with a gastric cancer diagnosis after surgery in an adult intensive care unit in a medical university hospital in Shenyang, China, from January 2010 to March 2011. Characteristics of patients and the length their ICU stay were gathered for analysis by univariate and multivariate Cox regression to examine the relationship with potential candidate factors. A regression tree was constructed to predict the length of ICU stay and explore the important indicators. Results: Multivariate Cox analysis found that shock and nutrition support need were statistically significant risk factors for prolonged length of ICU stay. Altogether, eight variables entered the regression model, including age, APACHE II score, SOFA score, shock, respiratory system dysfunction, circulation system dysfunction, diabetes and nutrition support need. The regression tree indicated comorbidity of two or more kinds of shock as the most important factor for prolonged length of ICU stay in the studied sample. Conclusions: Comorbidity of two or more kinds of shock is the most important factor of length of ICU stay in the studied sample. Since there are differences of ICU patient characteristics between wards and hospitals, consideration of the data-mining technique should be given by the intensivists as a length of ICU stay prediction tool.

• 동의신경정신과학회지
• /
• 제22권3호
• /
• pp.13-22
• /
• 2011

Objectives : This study was to research the relationship between Hwa-Byung and Framingham coronary risk score(FRS), cardiovascular disease. Methods : 649 people participated in the community based cohort study in Wonju City of South Korea from July 2nd to August 30th in 2006. Educated investigators checked up systolic & diastolic blood pressure and surveyed Hwa-Byung Diagnostic Interview Schedule(HBDIS), cohort questionnaire about gender, age, smoking, diabetes. Blood sample was collected from participants to analyze total cholesterol, HDL-cholesterol. FRS was calculated from collected data. 10-year prediction of coronary heart disease was determined from FRS by using score sheet that is estimated by Wilson et al. Collected data were analyzed by the chi-square test. Results : 1. Low risk number of people was 18(52.9%) in Hwa-Byung group, 263(42.8%) in non Hwa-Byung group. p-value was 0.472. Difference of the two group was invalid. 2. The number of people below or equal to average 10-year prediction of coronary heart disease as gnder & age, Hwa-Byung group was 19(55.9%), non Hwa-Byung group was 412(67.0%). p-value was 0.251. Difference of the two group was invalid. Conclusions : There was no correlationship Between Hwa-Byung and 10-year prediction of coronary heart disease.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 가을 학술발표논문집 Vol.31 No.2 (2)
• /
• pp.265-267
• /
• 2004

경제 여건의 향상 및 생활양식의 변화로 최근 우리나라에서도 당뇨병 환자가 늘어남에 따라 당뇨병의 예측 및 치료가 중요한 관심사가 되고 있다. 본 논문은 1993년과 1995년 두 차례에 걸쳐 경기도 연천 지역 주민들의 여러 가지 신체 지수 등을 조사한 데이터를 대상으로, 1차 년도의 데이터로부터 동일한 환자가 2차 년도에 정상상태를 유지하는지 흑은 당뇨병으로 진행이 되는지를 예측하는 문제를 다룬다. 혈당량, 허리둘레 등의 수치가 당뇨병의 발병에 영향을 끼치는 것은 알려진 사실이므로, 현재의 데이터로부터 앞으로의 발병 가능성을 예측하는 것이 가능하며, 이는 환자에게 보다 정확한 정보를 알려줄 수 있으므로 의미가 있는 일이다. 예측을 위해 본 논문에서는 분류기를 사용하며, 예측율을 높이기 위해 여러 분류기를 BKS로 결합하였다. BKS (behavior knowledge space) 결합 방법은 분류기간의 독립 가정이 필요 없으며, 데이터 크기가 크고 전형적인 경우에 좋은 결과를 낼 수 있는 방법이다. BKS 결합 방법을 통해 실험을 해본 결과 단일 분류기로 실험을 한 결과보다 향상된 성능을 얻을 수 있었으며, 투표 결합 방법과 비교하여 더 좋은 성능을 보였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.201-203
• /
• 2022

최근 5년간 당뇨병으로 진료받은 환자가 322만 명으로 27.7% 증가하였으며 여전히 손가락 채혈을 통해 혈당을 확인하므로 연속적인 혈당 측정과 혈당 피크 확인이 어렵고 고통스러워한다. 이를 해결하기 위해 14일 간 측정한 혈당 데이터를 기반으로 인공지능 기술을 사용하여 3개월간의 혈당 예측 데이터를 당뇨 환자들에게 제공해준다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2024년도 제69차 동계학술대회논문집 32권1호
• /
• pp.37-38
• /
• 2024

본 연구에서는 순천향대학교 천안병원에서 제2형 당뇨병 입원 환자를 대상으로 연속 혈당 측정기(CGM)를 통해 일주일 동안 수집된 101명의 혈당치 데이터를 사용하였다. 혈당치의 120분 동안 수집된 데이터를 기반으로 30분 후의 혈당치를 예측하는 트랜스포머 모델을 제안한다. 이는 트랜스포머의 인코더 모델만을 사용한 거보다 성능이 평균 제곱근 오차 (RMSE) 기준 약 4배 정도 향상하였으며, 이는 트랜스포머의 디코더 모델이 성능 향상에 효과적임을 보인다.

• 대한한의학회지
• /
• 제27권1호
• /
• pp.118-129
• /
• 2006

Objectives : A human being is classified into 4 constitutions(Taeyangin, Soyangin, Taeumin, and Souemin) and each constitution has the different incidence, treatment and prevention of disease in Sasang Constutional Medicine[SCM], The purpose of this study is to find relative risk(RR)s of each risk factors including Sasang Constitution[SC] for incidence of ischemic stroke. Methods : In 344-case patients with ischemic stroke and 1446 healthy control subjects without ischemic stroke, we evaluated sex, age. height, weight, BMI, ECG abnormality, hypertension, diabetes mellitus, blood lipid level and SC. These data were statistically analysed to investigate the relations between risk factors and the incidence of ischemic stroke by chi-square test. And then significant factors were analysed to get each adjusted odds ratio[OR] by binary logistic regression analysis. Results : ECG abnormality, hypertension, diabetes mellitus, HDL(high density lipoprotein) cholesterol, and SC were significantly related to the incidence of ischemic stroke, while age, sex and BMI were adjusted in a binary logistic regression analysis. Especially in SC, the incidence of ischemic stoke in Tae-eumin and Soyangin were higher than that in Soeumin (Tae-eumin OR=11.68[95% CI: 6.26-21.80], Soyangin OR=4.64[95% CI: 2.66-8.10]). Conclusions : These results suggested that SC may be one of important risk factors for ischemic stroke and it should be a useful data for prediction of incidence of ischemic stroke.

• Journal of Korean Neurosurgical Society
• /
• 제59권4호
• /
• pp.346-351
• /
• 2016

Objective : Early progressive infarction (EPI) is frequently observed and related to poor functional outcome in patients with middle cerebral artery (MCA) infarction caused by MCA occlusion. We evaluated the perfusion parameters of magnetic resonance imaging (MRI) as a predictor of EPI. Methods : We retrospectively analyzed patients with acute MCA territory infarction caused by MCA occlusion. EPI was defined as a National Institutes of Health Stroke Scale increment ${\geq}2$ points during 24 hours despite receiving standard treatment. Regional parameter ratios, such as cerebral blood flow and volume (rCBV) ratio (ipsilateral value/contralateral value) on perfusion MRI were analyzed to investigate the association with EPI. Results : Sixty-four patients were enrolled in total. EPI was present in 18 (28%) subjects and all EPI occurred within 3 days after hospitalization. Diabetes mellitus, rCBV ratio and regional time to peak (rTTP) ratio showed statically significant differences in both groups. Multi-variate analysis indicated that history of diabetes mellitus [odds ratio (OR), 6.13; 95% confidence interval (CI), 1.55-24.24] and a low rCBV ratio (rCBV, <0.85; OR, 6.57; 95% CI, 1.4-30.27) was significantly correlated with EPI. Conclusion : The incidence of EPI is considerable in patients with acute MCA territory infarction caused by MCA occlusion. We suggest that rCBV ratio is a useful neuro-imaging parameter to predict EPI.

• 보건행정학회지
• /
• 제26권3호
• /
• pp.185-194
• /
• 2016

Background: The purpose of this study is to forecast changes in the prevalence of chronic diseases and health expenditure by age group. Methods: Based on the Future Elderly Model, this study projects the size of Korean population, the prevalence of chronic diseases, and health expenditure over the 2014-2040 period using two waves (2012, 2013) of the Korea Health Panel and National Health Insurance Service database. Results: First, the prevalence of chronic diseases increases by 2040. The population with hypertension increases 2.04 times; the diabetes increases 2.43 times; and the cancer increases 3.38 times. Second, health expenditure on chronic diseases increases as well. Health expenditure on hypertension increases 4.33 times (1,098,753 million won in 2014 to 4,760,811 million won in 2040); diabetes increases 5.34 times (792,444 million won in 2014 to 4,232,714 million won in 2040); and cancer increases 6.09 times (4,396,223 million won in 2014 to 26,776,724 million won in 2040). Third, men and women who belong to the early middle-aged group (44-55 years old) as of 2014, have the highest increase rate in health spending. Conclusion: Most Korean literature on health expenditure estimation employs a macro-simulation approach and does not fully take into account personal characteristics and behaviors. Thus, this study aims to benefit medical administrators and policy makers to frame effective and targeted health policies by analyzing personal-level data with a microsimulation model and providing health expenditure projections by age group.

• 한국융합학회논문지
• /
• 제10권3호
• /
• pp.23-30
• /
• 2019

본 연구는 당뇨병 치료제 후보약물 정보를 이용하여 항당뇨에 영향을 미치는 물질구조를 발견하는데 목적이 있다. 정량적구조 활성관계를 이용한 기계 학습 모델을 만들고 부분최소자승 알고리즘을 통해 실험데이터 별로 결정계수를 파악한 후 변수중요도척도를 활용하여 주요 분자표현자를 도출하였다. 연구 결과, 후보약물 구조정보를 반영한 molecular access system fingerprint 데이터로 분석한 결과가 in vitro 데이터를 이용한 분석 결과보다 설명력이 높았으며, 항당뇨에 영향을 미치는 주요 분자표현자 역시 다양하게 도출할 수 있었다. 제안된 항당뇨 예측 및 주요인자 분석 방법을 활용한다면 유사한 과정을 반복 실험하는 기존 신약개발 방식과는 달리, 많은 비용과 시간이 소요되는 후보물질 스크리닝 (screening) 기간을 최소화하고, 신약개발 탐색기간도 단축하는 계기가 될 수 있을 것으로 기대한다.