• 한국빅데이터학회지
• /
• 제6권1호
• /
• pp.51-62
• /
• 2021

의료 인공지능 분야에서 의사의 판단에 도움을 줄 수 있는 질환 예측 및 분류 알고리즘에 대해선 많은 연구가 이뤄져왔지만, 의료 소비자의 정보 획득과 판단에 도움을 줄 수 있는 인공지능에 대해선 상대적으로 관심이 적다. 네이버 지식인에 지난 1년 간 자신의 증상엔 어떤 병원을 가야할 지 질문하는 질문 건수만 해도 15만 건이 넘는다는 사실은 의료소비자들에게 적합한 의료정보의 제공이 필요하다는 반증이기도 하다. 따라서 본 연구에선 의료소비자들이 자신의 증상에 대한 진료과목을 선택하는데 도움을 줄 수 있도록 네이버 지식인에서 환자들이 직접 서술한 증상 텍스트를 수집하여 8개 진료과목을 분류하는 분류모델을 구축했다. 우선 환자의 주관이 개입된 데이터의 타당성과 객관성을 확보하기 위해 객관적 증상 텍스트(서울응급의료 정보센터에서 정리한 진료과목 별 주요 질환 증상)와 주관적 증상 텍스트(지식인 데이터) 간 유사도 측정을 수행하였다. 유사도 측정 결과, 두 텍스트가 동일한 진료과목의 증상일 경우 상이한 진료과목의 증상 텍스트에 비해 상대적으로 높은 유사성을 가진다는 것을 입증했다. 상기 절차를 따라 타당성을 확보한 주관적 증상 텍스트를 대상으로 릿지회귀모델을 사용하여 분류모델을 구축한 결과 0.73의 정확도를 확보할 수 있었다.

• Journal of Community Nutrition
• /
• 제7권3호
• /
• pp.135-140
• /
• 2005

This study was conducted to evaluate the health status of staff by medical examination data according to the work classification as professional, office worker and laborer in K University in Seoul, Korea. Two thousand four hundred and eighty-four staff (men : 1154, female: 1330) from the university were studied for this report. The anthropometric (height, weight and BMI) and blood pressure (systolic, diastolic) and biochemical parameters (hemoglobin, glucose, cholesterol, AST, ALT) were measured. All groups were calculated using GLM multivariate analysis for three groups after adjustment for age. The average BMI was significantly higher in laborers than professionals and officers after adjustment for age. In blood pressure, especially in SBP, the significant difference was found in females according to the job classification. Blood glucose levels of female laborers were significantly higher than those of officers and professionals. The level of blood total cholesterol of male professionals was significantly higher than those of laborers. The level of blood total cholesterol of female laborers was significantly higher than officers or professionals. Importantly, significant differences were found in BMI, SBP, blood glucose level and cholesterol level of female staff after adjustment for age. These results showed that there were differences in health subjects of staff according to the work classification. This study would provide basic data to prepare the program of health promotion for the college staff according to work classification. Further research is required to discover factors influencing health promotion of staff in colleges.

• Communications for Statistical Applications and Methods
• /
• 제27권2호
• /
• pp.225-239
• /
• 2020

Analysis approaches for single compositional data are well established; however, effective analysis strategies for paired compositional data remain to be investigated. The current project was motivated by studies of age-related hearing loss (presbyacusis), where subjects are classified into four audiometric phenotypes that need to be ranked within these phenotypes based on their paired compositional data. We address this challenge by formulating this problem as a classification problem and integrating a penalized multinomial logistic regression model with compositional data analysis approaches. We utilize Elastic Net for a penalty function, while considering average, absolute difference, and perturbation operators for compositional data. We applied the proposed approach to the presbyacusis study of 532 subjects with probabilities that each ear of a subject belongs to each of four presbyacusis subtypes. We further investigated the ranking of presbyacusis subjects using the proposed approach based on previous literature. The data analysis results indicate that the proposed approach is effective for ranking subjects based on paired compositional data.

• 대한한의학회지
• /
• 제28권1호통권69호
• /
• pp.35-41
• /
• 2007

Objectives : To gain better insights on the characteristics of stroke patients admitted to oriental medical hospitals, we analyzed the data of 363 consecutive patients with acute ischemic stroke from Hanbang Stroke Registry supported by the Ministry of Science and Technology of Korea. Methods : Subjects' enrollment was in the oriental medical hospitals of 3 universities located in the metropolitan region from October 2005 to October 2006. We assessed the subjects' general characteristics, risk factors, and etiology of stroke. Each patient's TOAST classification type was confirmed by two independent specialists. Those were small vessel occlusion (SVO), large artery atherosclerosis (LAA), cardioembolism (CE), stroke with other determined etiology (SOE), and stroke with undetermined etiology (SUE).Results 'The distribution of the subjects' general characteristics and risk factors for stroke were similar with result storm previous reports. However, in the TOAST classification, SVO was the major type occupying 78.5% in the total subjects, which is the highest share compared with other research with similar methods. These results imply that patients with more severe symptoms rarely visit oriental medical hospitals. Conclusion : Assuming that this research will continue adding patient's data continuously, this work will help us to understand the features of stroke patients at oriental medical hospitals, and contribute to expansion of the Korean Hanbang Stroke Data Bank.

• 대한기관윤리심의기구협의회지
• /
• 제5권1호
• /
• pp.21-32
• /
• 2023

Purspose: The purpose of this study is to examine the meaning and definition of vulnerable subjects in clinical trials in light of domestic and international regulations and guidelines, to analyze the contents of standard operation procedures (SOPs) among advanced general hospitals in Korea that conduct clinical trials, and to examine deliberation procedures for operation plans. Methods: The study examined how vulnerable research subjects were defined and described in related regulations and the classification of vulnerable research subjects presented in the IRB/HRPP SOPs of 18 clinical trial institutions, including 11 AAHRPP-accreditated general hospitals in Korea, as well as the operation of the IRB deliberation. Results: Among all domestic and international regulations and guidelines, only the The Council for International Organization of Medical Sciences (CIOMS) guidelines explain why vulnerability is related to judgments on the severity of physical, psychological, and social harm, why individuals are vulnerable, and for what reasons. However, the classification of vulnerable subjects by institutions differed from the classification by the International Conference on Harmonization-Good Clinical Practice (ICH-GCP). A total of the 16 institutions classified children and minors as vulnerable research subjects. 14 institutions classified subjects who cannot consent freely were classified as vulnerable subjects. 15 institutions classified sujects who can be affected by the organizational hierarchy were classified as vulnerable subjects. Subjects in emergency situations were regarded as vulnerable research subjects in 8 of institutions, while people in wards, patients with incurable diseases, and the economically poor including the unemployed were categorized as vulnerable research subjects in 7, 4, and 4 of institutions, respectively. Additionally, some research subjects were not classified as vulnerable by ICH-GCP but were classified as vulnerable by domestic institutions 15 of the institutions classified pregnant women and fetuses as vulnerable, 11 classified the elderly as vulnerable, and 6 classified foreigners as vulnerable. Conclution: The regulations and institutional SOPs classify subjects differently, which may affect subject protection. There is a need to improve IRBs' classifications of vulnerable research subjects. It is also necessary to establish the standards according to the differences in deliberation processes. Further, it is recommended to maintain a consistent review of validity, assessment of risk/benefit, and a review using checklists and spokeperson. The review of IRB is to be carried out in a manner that respects human dignity by taking into account the physical, psychological, and social conditions of the subjects.

• 대한한의학회지
• /
• 제25권4호
• /
• pp.209-219
• /
• 2004

The author investigated whether ACE/DD, AGN/TT, and ApoE/ε4 genotypes are associated with CI and whether genetic risk is enhanced by Sasang constitutional classification. The author ascertained these genotypes in patients with CI (n=211), diagnosed by brain computed tomography. Control subjects for the infarction group were randomly selected from 319 subjects matched for age, gender, and history of hypertension with patients. The ACE/DD genotype was not associated with CI. However. there was significant association between ApoE polymorphism and CI (x²=15.089, p<.05). Furthermore, frequency of AGN/TT genotype was higher in the patients with CI than in the controls (x²=20.072, p<.05). The frequency of T allele Was 0.91 in patients and 0.82 in controls (x²=17.237, p<.05). However, the Sasang constitutional classification did not increase the relative risk for CI in the subjects with ApoE/ε4 or AGN/T allele. These results suggest that ApoE and AGN polymorphism predict CI. but Sasang constitutional classification does not enhance the risk for CI associated with ApoE/ε4 or AGN/TT in a Korean population.

• 사상체질의학회지
• /
• 제21권3호
• /
• pp.39-47
• /
• 2009

1. Objectives: In order to classify an individual into four constitution type, an oriental medical doctor utilizes various information such as face, pulse, voice, and questionnaire. When only one type of information is used, one's constitution may not be decided correctly. 2. Methods: In this paper, we propose a novel four constitution types classifier using facial images which classifies subjects into indecision group as well as Taeumin, Soeumin, and Soyangin. 3. Results: Experimental results show that it increases the classification rate though the decision rate is rather decreased, which is more effective and reliable than conventional classifiers without indecision. 4. Conclusion: For the effective classification, we have found that it is more useful to add an indecision group which requires more information to be properly classified into one constitution type.

• 대한의용생체공학회:의공학회지
• /
• 제37권2호
• /
• pp.61-67
• /
• 2016

This paper presented a method for random forest based the arrhythmia classification using both heart rate (HR) and heart rate variability (HRV) features. We analyzed the MIT-BIH arrhythmia database which contains half-hour ECG recorded from 48 subjects. This study included not only the linear features but also non-linear features for the improvement of classification performance. We classified abnormal ECG using mean_NN (mean of heart rate), SD1/SD2 (geometrical feature of poincare HRV plot), SE (spectral entropy), pNN100 (percentage of a heart rate longer than 100 ms) affecting accurate classification among combined of linear and nonlinear features. We compared our proposed method with Neural Networks to evaluate the accuracy of the algorithm. When we used the features extracted from the HRV as an input variable for classifier, random forest used only the most contributed variable for classification unlike the neural networks. The characteristics of random forest enable the dimensionality reduction of the input variables, increase a efficiency of classifier and can be obtained faster, 11.1% higher accuracy than the neural networks.

• 디지털융복합연구
• /
• 제10권10호
• /
• pp.347-352
• /
• 2012

본 연구에서는 2011년1월1일부터 2011년 6월 30일까지 6개월 동안 대학병원 응급실로 방문하여 내과로 입원한 환자 889명을 조사대상으로 응급의료센터에 방문한 환자의 주호소와 주진단에 대한 분포를 확인하고, 기존의 질병분류 방법인 ICD와 일차 진료를 세부 분류하는 방법인 ICPC를 비교하고자 하였다. 분석방법으로는 환자들의 인구통계학적인 측면을 살펴보기 위해 빈도분석이 시행되었으며, ICD와 ICPC에 따른 주호소 분포를 알아보기 위한 교차분석을 시행하였다. 다음과 같이 분석을 시행한 결과 주증상중 Abdominal pain이 17.7%, dyspnea가 13.5%, Fever가 12.5% haematemesis가 9.8%로 주로 일차의료에서 사용되는 주호소 증상이 전체의 54.5%를 차지하는 것으로 나타나 응급의료센터에서 일차 진료 분류법을 사용하는데 적합한 것으로 예상되었다. 또한 진단명중 abdominal pain의 경우 ICD에서 R10으로 116(18.7%)명이 분류되었지만 ICPC에서는 epigastric(11.5%)과 general(5.8%)로 나뉘어 분류되어 세분화 되는 것으로 나타났다. 즉, 현재 병원에서 시행되고 있는 ICD 분류법 보다는 일차 진료 분석에 초점이 맞춰진 ICPC 분류법이 좀 더 세분된 환자분류에 용이하다는 것을 알 수 있다. 비록 본 조사에 사용된 자료가 1개 병원에 그치고 있어서 자료의 대표성이 확보되기는 어렵지만, ICPC가 응급의료에 있어 분류가 가능하고 기존의 분류법 보다 세분된 환자분류가 용이하다는 점에서 그 의의가 있다.

• The Journal of Korean Physical Therapy
• /
• 제4권1호
• /
• pp.43-57
• /
• 1992

This study was conducted from August, 1980 to March, 9991 to the 40 subjects who were admitted to Kosin Medical Center and received rehabilitation treatment and discharged under the impression of stroke. The objectives are to evaluate the function of the activites of daily living and comprehensive function and find the status of rehabilitation treatment by Modified Barthel Index and PULSES Profile when first requested or rehabilitation treatment(T1), at 2 weeks after rehabilitation treatment(T2), at discharge(T3) and at the time of ambulatory treatment after 2 weeks(T4). The study materials were clinical charts and functional evaluation sheets, and the results are as follows : 21 subject$(52.5\%)$ were male, 19 subjects$(47.5\%)$ were female, and the age distribution was from 19 to 70 in age, the average age was 52.7. By the classification of diagnosis, 21 subjects$(52.5\%)$ were cerebral hemorrhage, 8 subjects$(20.2\%)$ were cerebral thrombosis, 6 subjects$(15.0\%)$ were cerebral embolism, and 5 subjects$(12.5\%)$ were cerebral infarction. The Barthel Index scores were 35.7, 54.5, 71.8, 88.7 on the average at T1, T2, T3, T4 respectively. The PULSES scores were 16.4, 13.7, 11.4, 8.7 on the average at T1, T2, T3, T4 respectively. Regarding the Pearson's correlation coefficient between the Barthel Index scores and the PULSES scores, it was -0.7991(P>0.001) at T1 and -0.8986(P>0.001) at T3, then beth of correlations were very high.