• Journal of Korean Academy of Nursing Administration
• /
• v.6 no.3
• /
• pp.375-388
• /
• 2000

This study was attempted to help in explore new direction about Clinical Classification System of the pediatric patients visiting emergency center. Data were collected from 276 patients who visited emergency center of E University Hospital during 3 months period form March 1, to May 31, 1999. The results were as follows: 1. Distribution of pediatric patients according to Clinical Classification System, class I(59.9%) topped followed by class II(23.9%), class III(14.1%), class IV(2.0%). Average score of pediatric patients according to Clinical Classification System showed class I.00, class II .02, class III .05, class IV .07. and total mean score of items lowed averaged .01. 2. With the resepect to the Clinical Classification System according to the pediatric patients visiting emergency center, there were stastically significant difference in visiting time($x^2=27.839$, P=.023), experience of admission($x^2=11.365$, p=.010), disease classification($x^2=89.998$, p=.000), state of airway patency($x^2=18.781$, p=.000), consciousness level($x^2=59.774$, p=.000), period of symptom manifestation($x^2=34.112$, p=.000), pediatric patients protector's thinking about pediatric patients state($x^2=49.998$, p=.000), treatment outcome($x^2=72.278$, p=.000), duration of stay at emergency center($x^2=103.062$, p=.000). 3. There were significant correlation between the state of pediatric patients and Clinical Classification System(r=.530, p=.000).

• Journal of Biomedical Engineering Research
• /
• v.31 no.4
• /
• pp.328-334
• /
• 2010

Over the past few years, a considerable number of methods have been proposed and applied for the classification of photoplethysmography (PPG). Most of the previous studies, however, focused on the qualitative description of the pulse type according to specific disease and thus provided ambiguous criteria to interpreters. In order to screen out this problem, we present a quantitative method for the pulse type classification including the second derivative of photoplethysmography (SDPTG). In the PPG signal, we have classified the signal as 4 types using the position and the presence of the dicrotic wave. In addition, we have categorized the SDPTG signal as 7 types using the position and the presence of "c" and "d" wave and the sign of "c" wave. In order to check the efficacy of the proposed pulse type classification rule, we collected pulse signals from 155 subjects with different ages and sex. From the correlation analysis, Class 1(p<0.01) and Class 2(p<0.01) in the PPG signal are significantly correlated with ages. In a similar manner Class A(p<0.01), Class C(p<0.05), Class D(p<0.01), and Class F(p<0.01) in the SDPTG signal are considerably correlated with the ages. From these observations, and some earlier ones [4], [5], we can conclude that since the newly proposed method has objectivity and clarity in pulse type classification, this method can be used as an alternative of previous classification rules including similar age-related characteristics.

• The Journal of Korean Medicine
• /
• v.35 no.3
• /
• pp.1-14
• /
• 2014

Objectives: The purpose of this study was to evaluate the achievements of Ryodoraku and to suggest new diagnostic ideas. Methods: A search of six Korean databases and one Japanese was performed using the terms such as Ryodoraku, diagnosis, foreigner, etc. and the search results classified and summarized. Results: From the initial search results, 21 Korean papers and 26 Japanese papers were selected and classified into 4 categories, that is, classification by pattern, classification by physiological limit, classification by setting various sections using the average Ryodoraku score, and classification by formula. Conclusions: Each of the 4 methods has its own benefits; however, it is hard to find disease-specific common characteristics from the Ryodoraku diagnostic values with the methods. Further studies which use the number of Pyesaek and Gyeokcha are necessary.

• The Korean Journal of Emergency Medical Services
• /
• v.24 no.1
• /
• pp.25-36
• /
• 2020

Purpose: We analyzed the characteristics and differences in patients' medical benefits and health insurance based on disease severity classification. Methods: We examined 29,139 patients who visited the emergency medical center of K Hospital from January 1,2016 to December 31, 2016. Survey items included the Korean Triage and Acuity Scale (KTAS) classification of emergency and non-emergency situations ratio and type of insurance. Results: According to KTAS classification, 76.2% of patients exhibited an emergency condition and 23.8% exhibited a non-emergency condition. Emergency patients exhibited more trauma than non-emergency patients. According to the type of insurance coverage, the duration of stay in the emergency room was longer for patients with medical care than for patients with health insurance. Additionally, 119 ambulances use was significantly higher among patients with medical care. Conclusion: Policy discussions should address alternative ways to replace the 119 ambulances used by patients in this study. Additionally, health care administrators should identify alternative care agencies as potential alternatives to emergency room visits.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.27 no.4
• /
• pp.383-390
• /
• 2013

In order to improve the integrating accuracy and to elevate the serviceability of the KM(Korean Medicine) ontology constructed by the Korea Institute of Oriental Medicine, this research simplified the many-to-many corresponding relationship between groups of methods of treatment and groups of accompanied symptoms from disease ontology and categorized systematically the relationship. We first extracted the combinations of methods of treatment and accompanied symptoms from the KM ontology, then categorized the attributes of combinations that their frequencies were over 10 times by analyzing KM terms definition and the basic KM theory. We constructed the classification hierarchy having 14 kinds of classification in 4 steps and extracted 450 meaningful combinations. This research improved the integrating accuracy and elevated the serviceability of KM information by the classification system.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.290-294
• /
• 1997

Chromosomes, as the genetic vehicles, provide the basic material for a large proportion of genetic investigations. The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We are employed three morphological feature parameters ; centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), as input in neural network by preprocessing twenty human chromosome images. The results of our experiments show that our TMANN classifier is much more useful in neural network learning and successful in chromosome classification than the other classification methods.

• Journal of Korean Society of Forest Science
• /
• v.99 no.6
• /
• pp.777-784
• /
• 2010

The purpose of this study was to develop evaluation indices for forest landscape classification. The indices were chosen to enable forest managers to establish effective landscape management strategies through three times of focus group interviews and email survey with experts. The 13 landscape evaluation indices were finally divided into four categories. They were ecological health (degree of green naturality, degree of ecological naturality, disease and insect damage, crown vitality), aesthetic visual quality (naturalness, harmony, diversity, traditionality, aesthetic appreciation, rarity), and sensitivity (level of tourism/recreational use), interruptions (damaged land, artificial structures). The five-level was suggested for the forest landscape classification system.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.163-171
• /
• 2019

Purpose: Purpose: The National Safety Experience Center Establishment and Reinforcement Project Management Guidelines, established to build a national safety experience center that is central to practicing education on disasters and safety accidents, requires that appropriate experience training programs be in place. However, due to the lack of classification grounds for the six areas of disaster•safety accidents presented by the Ministry of Public Administration and Security, and the mortality statistics necessary for establishing sectors have accumulated for over a decade, they are based on this. Our purpose is to standardize classification of sectors belonging to each area. Methods: We will divide disaster•safety accidents into 6 areas by three steps, and the grounds for 6 areas of accidents are presented. The 15 external causes other than the disease since 2009 has been proposed by The National Statistical Office. Therefore on the basis of these causes, various sectors belonging to each area are classified. Results: We will divide all disaster•safety accidents into six areas through three logical separation stages, and the areas were systematically classified based on the 15 factors of death. In conclusion, we present the grounds for the classification criteria in the six areas, the transportation accident disaster area in three areas, the social infrastructure system area in four areas, the crime accident disaster area in four areas, the life safety accident area in four areas, we set up all disaster•safety accidents in six areas and finally standardize total 25 areas.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.4
• /
• pp.69-77
• /
• 2018

The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert's labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert's labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.