• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.19-21
• /
• 2006

Single Nucleotide Polymorphism(SNP)는 인간 유전자 서열의 0.1%에 해당하는 부분으로 이는 각 개인의 체질 및 각종 유전질환과 밀접한 관련이 있다고 알려져 있다. 최근 이 SNP정보의 패턴을 이용 질병의 진단 및 치료에 연관지으려는 노력이 시도되고 있다. 그러나 아직 SNP를 이용한 효율적인 분석방법에 대한 전산학적 연구는 많지 않다. 본 논문에서는 대표적인 패턴인식기 중 하나인 Support Vector Machine(SVM)을 이용 한국인의 대표적인 유전질환으로 알려진 만성간염에 대해서 관련된 SNP에 대한 패턴 인식율 측정을 실험하였다. 실험 데이터는 간 및 소화기 질환 유전체 센터에서 얻어진 만성간염 환자와 관련 SNP정보를 사용하였으며, 실험 결과 전체 SNP 정보를 모두 가지는 환자그룹에 대한 학습인식율이 66.46%로 나타났으며, 부분그룹에서는 72.91%로 높은 인식율을 보였다. 이 결과는 SNP 정보를 이용한 만성간염의 초기진단예측에 SVM을 효율적으로 사용할 수 있음을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.85-87
• /
• 2006

압타머칩은 (주)제노프라에서 개발한 새로운 개념의 바이오칩으로서, 압타머(aptamer)를 이용하여 혈액중의 특정 단백질군의 상대적인 양의 변화를 측정할 수 있으며, 질병 진단에 바로 응용할 수 있는 도구이다. 본 논문에서는 압타머칩 데이터 분석을 통해 심혈관 질환 환자의 질병 진행 단계를 예측할 수 있음을 보인다. 정상, 안정/불안정성 협심증, 심근경색의 네 단계로 표지된 환자의 혈액 샘플로부터 제작한 (주)제노프라의 3K 압타머칩 데이터를, 일반 DNA 마이크로어레이 분석과 동일한 과정을 거쳐 분류한 결과, 각 단계별 환자샘플이 확연히 구분되는 것을 확인하였다. 분산분석 결과 P-Value를 이용하여 자질 선택을 수행하고, 분류 알고리즘으로는 신경망, 결정트리, SVM, 베이지안망을 적용한 결과. 각 알고리즘별로 50대 남성환자 31개의 샘플에 대하여 $77{\sim}100%$의 정확도로 심혈관 질환의 단계를 구분해내었다.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.245-257
• /
• 2015

This study was to develop the predictive model for severity-adjusted mortality of inpatients with multiple chronic conditions and analyse the factors on the variation of hospital standardized mortality ratio(HSMR) to propose the plan to reduce the variation. We collect the data "Korean National Hospital Discharge In-depth Injury Survey" from 2008 to 2010 and select the final 110,700 objects of study who have chronic diseases for principal diagnosis and who are over the age of 30 with more than 2 chronic diseases including principal diagnosis. We designed a severity-adjusted mortality predictive model with using data-mining methods (logistic regression analysis, decision tree and neural network method). In this study, we used the predictive model for severity-adjusted mortality ratio by the decision tree using Elixhauser comorbidity index. As the result of the hospital standardized mortality ratio(HSMR) of inpatients with multiple chronic conditions, there were statistically significant differences in HSMR by the insurance type, bed number of hospital, and the location of hospital. We should find the method based on the result of this study to manage mortality ratio of inpatients with multiple chronic conditions efficiently as the national level. So we should make an effort to increase the quality of medical treatment for inpatients with multiple chronic diseases and to reduce growing medical expenses.

• Pediatric Infection and Vaccine
• /
• v.10 no.2
• /
• pp.215-222
• /
• 2003

Purpose : This study was to analyze serious bacterial infections in infants younger than three months of age and to review the direction of treatments for these patients. Methods : 378 febrile infants with a rectal temperature ${\geq}38.0^{\circ}C$ visited from Jan. 2001 through Dec. 2002 were retrospectively studied. Infants with the following criteria belonged to the low risk group. WBC $5,000{\sim}15,000/mm^3$, WBC negative in urine stick test and negative for nitirite test, CSF WBC < $10/mm^3$ and negative in CSF gram stain, negative chest X-ray, stool WBC <5/HFP(high power field), and focal infection. If any of the above criteria were not met, they belonged to the high risk group. SBI was defined as a positive culture of urine, blood or CSF. SI was defined as aseptic meningitis or pneumonia including above laboratory tests of SBI. SBI patients were separately compared with two groups, high risk and low risk. Results : Of the 378 infants that were tested 216(57.1%) were in the high risk group and 162(42.9%) in the low risk group. Among 105 SBI(27.8%) and 172 SI(45.5%), there were 98 urinary tract infection(25.2%), 10 bacteremia(2.6%), 2 bacterial meningitis(0.6%), and 77 aseptic meningitis(22.8%). There were 76 SBI(35.2%) from the high risk group and 29 SBI(17.9%) from the low risk group identified. The results of the sensitivity(72.4%), the specificity(48.7%), the negative predictive value(82.1%) and the positive predictive value (35.2%) were calculated. Conclusion : Even though the probability of SBI in the low risk group is insignificant, it should still be considered in febrile infants younger than 3 months of age. I believe the CSF study is necessary because of the moderate high incidence of abnormal finding in our study.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.215-224
• /
• 2010

Most chronic diseases are complex diseases which are caused by interactions of several genes. Studies on finding SNPs and gene-gene interactions involved in the development of complex diseases can contribute to prevention and treatment of the diseases. Previous studies mostly concentrate on finding only the set of SNPs involved. In this study we suggest a way to see how these SNPs interact using boolean expressions. The proposed method consists of two stages. In the first stage we find the set of SNPs involved in the development of diseases using mutual information based on entropy. In the second stage we find the highest accuracy boolean expression that consists of the SNP set obtained in the first stage. We experimented with clinical data to demonstrate the effectiveness of the proposed method. We also compared the differences between our method and the previous results on the SNP associations studies.

• Journal of Digital Convergence
• /
• v.16 no.2
• /
• pp.251-259
• /
• 2018

This study aimed to identify the risk factors for cardiovascular disease (CVD) among age groups using the Framingham risk score (FRS). The research design used was a cross sectional descriptive study using the Sixth Korean National Health and Nutrition Examination Survey from 2013-2015. Data from 5211 men, between the ages of 30-74 was analyzed. After adjusting for age, the result of logistic regression analysis showed that obesity (OR=2.51 95% CI=2.05-3.07), physical inactivity (OR=1.71, 95% CI=1.39-2.10), heavy alcohol drinking (OR=1.33, 95% CI=1.09-1.62), and dietary fiber intake (OR=0.99, 95% CI=0.98-0.99) were presented as predictors of CVD. Obesity was considered to be a particularly important predictor of CVD for young and middle-aged men. This result will be used for developing intervention relating to lifestyle modification for young and middle-aged men.

• Journal of Chest Surgery
• /
• v.30 no.12
• /
• pp.1205-1213
• /
• 1997

This study reviewed useful aspects of the intraoperative transesophageal echocardiography among the patients in whom heart surgery were undertaken between January 1996 and July 1996 at St.Pauls hospital, Medical College of Catholic University, Seoul, Korea. During that period, 61 patients were operated on because of valvular heart disease(25 patients), coronary artery disease(22 patients), congenital heart disease(13 patients), and combined coronary artery disease and valvular heart disease(1 patient). Two patients(1 redo-VSD and 1 valvular heart diease) needed repeated aortic cross clamping and complementary procedures because of incomplete initial procedures. There was no incidence of air embolism. We could observe significant relationship of cardiac output monitoring methods either by thermodilution technique and transesophageal echocardiography by linear regression analysis(p<0.001). We tested myocardial response(percentage of systolic wall thickness, PSWT) with low dose dobutamine challenge to predict post-CABG myocardial perfusion. And the test showed statistically significant resp.onse(sensitivity 76%, specificity 94.7%, positive predictive value 95%, negative predictive value 75%). These results suggest that cardiac surgeon could draw more benefits by intraoperative transesophageal echocardiography.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10a
• /
• pp.28-32
• /
• 2006

최근 연구결과에 의하면 심장질환을 포함한 심혈관질환은 성별에 관계없이 미국 및 전 세계적으로 질병사망의 주요 원인으로 조사되었다. 본 연구에서는 보다 효율적으로 진단하기 위해 진단의사 결정 보조시스템에 대해서 다룬다. 개발된 시스템은 혈청 내의 특정 단백질의 상대적 양을 측정할 수 있는 바이오칩인 압타머칩을 이용해 생성한 환자들의 칩 데이터를 Support Vector Machine, Neural Network, Decision Tree, Bayesian Network 등의 총 4가지 기계학습 알고리즘으로 분석하여 질환단계를 예측하고 진단을 위한 보조정보를 제공한다. 논문에서는 총 135개 샘플로 구성된 3K 압타머칩 데이터에 대해 측정된 초기 시스템의 질환단계 분류성능을 제시하고 보다 유용한 진단의사결정 보조 시스템을 구성하기 위한 요소들에 대해서 논의한다.

• Journal of Internet of Things and Convergence
• /
• v.6 no.4
• /
• pp.7-14
• /
• 2020

This study analyzed the effect of the number of deaths of circulatory system diseases according to 12-day short-term exposure of carbon monoxide from January 2010 to December 2018, and predicted the future treatment cost of circulatory system diseases according to increased carbon monoxide concentration. Data were extracted from Air Korea of Korea Environment Corporation and Korea Statistical Office, and analyzed using Poisson regression analysis and ARIMA intervention model. For statistical processing, SPSS Ver. 21.0 program was used. The results of the study are as follows. First, as a result of analyzing the relationship between the impact of short-term carbon monoxide exposure on death of circulatory system diseases from the day to the previous 11 days, it was found that the previous 11 days had the highest impact. Second, with the increase in carbon monoxide concentration, the future circulatory system disease treatment cost was estimated at 10,123 billion won in 2019, higher than the observed value of 9,443 billion won at the end of December 2018. In addition, when summarized by month, it can be seen that the cost of treatment for circulatory diseases increases from January to December, reflecting seasonal fluctuations. Through such research, the future for a healthy life for all citizens can be realized by distributing various devices and equipment utilizing IoT to preemptively respond to the increase in air pollutants such as carbon monoxide.

• The Science & Technology
• /
• no.3 s.418
• /
• pp.106-107
• /
• 2004