• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.51-62
• /
• 2021

In the field of medical artificial intelligence, there have been a lot of researches on disease prediction and classification algorithms that can help doctors judge, but relatively less interested in artificial intelligence that can help medical consumers acquire and judge information. The fact that more than 150,000 questions have been asked about which hospital to go over the past year in NAVER portal will be a testament to the need to provide medical information suitable for medical consumers. Therefore, in this study, we wanted to establish a classification model that classifies 8 medical subjects for symptom text directly described by patients which was collected from NAVER portal to help consumers choose appropriate medical subjects for their symptoms. In order to ensure the validity of the data involving patients' subject matter, we conducted similarity measurements between objective symptom text (typical symptoms by medical subjects organized by the Seoul Emergency Medical Information Center) and subjective symptoms (NAVER data). Similarity measurements demonstrated that if the two texts were symptoms of the same medical subject, they had relatively higher similarity than symptomatic texts from different medical subjects. Following the above procedure, the classification model was constructed using a ridge regression model for subjective symptom text that obtained validity, resulting in an accuracy of 0.73.

• Journal of Community Nutrition
• /
• v.7 no.3
• /
• 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
• /
• v.27 no.2
• /
• 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.

• The Journal of Korean Medicine
• /
• v.28 no.1 s.69
• /
• 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.

• The Journal of KAIRB
• /
• v.5 no.1
• /
• 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.

• The Journal of Korean Medicine
• /
• v.25 no.4
• /
• 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.

• Journal of Sasang Constitutional Medicine
• /
• v.21 no.3
• /
• 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.

• Journal of Biomedical Engineering Research
• /
• v.37 no.2
• /
• 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.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.347-352
• /
• 2012

As medical treatment is developing with technology, the men's average life expectancy is extended. Therefore, primary medical care becomes emphasized in order to reduce the medical expenses in the long term by satisfying individual's life being healthy. The date for this thesis was collected from January 2011 to June 2011. 889 patients who visited the university hospital emergency room and hospitalized in internal medicine, were picked as the research subjects and they were targeted to be recorded the distribution of chief complaint and principal diagnosis of the patients. Also, this record was used to apply to the standard Classification of Diseases(as known as ICD) and the method of detailed classification of the primary medical care(as known as ICPC) to compare each other. In order to analysis, frequency analysis was used to see vital statistics and the cross tabulations were used to see the distribution of chief complaint according to ICD and ICPC. Results of the research were Abdominal pain(17.7%), Dyspnea(13.5%), Fever (12.5%), and Haematemesis (9.8%), and those symptoms represented the 54.5% of overall chief complaints that is treated in primary care. Therefore, it is acceptable to use the classification of the primary medical care at doc-in-a-box. Also, in case of diagnosis of abdominal pain, it is classified to R10 in ICD and 116 patients(18.7%) belonged to it, but according to ICPC, it is subdivided to Epigastric(11.5%) and General(5.8%). ICPC classification, which is focused to primary medical care is more detailed than ICD classification. Because the data that is collected for this thesis is from only one hospital, it is hard to represent to all the cases, but ICPC in emergency medical care, it has more classification available and it can subdivide the patients effectively, so it is meaningful.

• The Journal of Korean Physical Therapy
• /
• v.4 no.1
• /
• 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.