• 생물정신의학
• /
• 제12권2호
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• 한국병원경영학회지
• /
• 제23권2호
• /
• pp.28-41
• /
• 2018

Purpose: This study purposed to analyze the spatial accessibility of mental health institutions in Ganwon-Do using Geographic Information System and to suggest policy implications. Methodology: Network analysis was applied to assess the spatial accessibility of mental health institutions in Gangwon-Do. To perform the network analysis, network data set was built using administrative district map, road network, address of mental health institutions in Gangwon-Do. After building network data set, Two network analysis methods, 1) Service area analysis, 2) Origin Destination cost matrix were applied. Service area analysis calculated accessive areas that were within specified time. And using Origin Destination cost matrix, travel time and road travel distance were calculated between centroids of Eup, Myeon, Dong and the nearest mental health institutions. Result: After the service area analysis, it is estimated that 19.63% of the total areas in Gangwon-Do takes more than 60 minutes to get to clinic institutions. For hospital institutions, 23.08% of the total areas takes more than 60 minutes to get there. And 59.96% of Gangwon-do takes more than 30 minutes to get to general hospitals. The result of Origin-Destination cost matrix showed that most Eup Myeon Dong in Gangwon-Do was connected to the institutions in Wonju-si, Chuncheon-si, Gangneung-si. And it showed that there were large regional variation in time and distance to reach the institutions. Implication: Results showed that there were regional variations of spatial accessibility to the mental health institutions in Gangwon-Do. To solve this problem, Several policy interventions could be applied such as mental health resources allocation plan, telemedicine, providing more closely coordinated services between mental health institutions and community mental health centers to enhance the accessibility.

• 보건행정학회지
• /
• 제27권3호
• /
• pp.229-240
• /
• 2017

Background: This study purposed to analyze the spatial accessibility of women in childbearing age to the healthcare organizations (HCOs) providing delivery services in Gangwon-do. Methods: Network analysis was applied to assess the spatial accessibility based on the travel time and road travel distance. Travel time and travel distance were measured between the location of HCOs and the centroid of the smallest administrative areas, eup, myeon, and dong in Gangwon-do. Korean Transport Database Center provided road network GIS (Geographic Information System) Database in 2015 and it was used to build the network dataset. Two types of network analysis, service area analysis and origin-destination (OD)-cost matrix analysis, applied to the created network dataset. Service area analysis defined all-accessible areas that are within a specified time, and OD-cost matrix analysis measured the least-cost paths from the HCOs to the centroids. The visualization of the number of the HCOs and the number of women in childbearing age on the Ganwon-do map and network analysis were performed with ArcGIS ver. 10.0 (ESRI, Redlands, CA, USA). Results: Twenty HCOs were providing delivery services in Gangwon-do in 2016. Over 50% of the women in childbearing age were aged more than 35 years. Service area analysis found that 89.56% of Gangwon-do area took less than 60 minutes to reach any types of HCOs. For tertiary hospitals, about 74.37% of Gangwon-do area took more than 60 minutes. Except Wonju-si and Hoengseong-gun, other regions took more than 60 minutes to reach the tertiary hospital. Especially, Goseong-gun, Donghae-si, Samcheok-si, Sokcho-si, Yanggu-gun, Cheorwon-gun, and Taebaek-si took more than 100 minutes to the tertiary hospital. Conclusion: This study provided that the accessibility toward the tertiary hospital was limited and it may cause problems in high-risk delivery patients such as over 35 years. Health policy makers will need to handle the obstetric accessibility issues in Gangwon-do.

• Annals of Clinical Neurophysiology
• /
• 제22권2호
• /
• pp.82-91
• /
• 2020

Electroencephalography (EEG) produces time-series data of neural oscillations in the brain, and is one of the most commonly used methods for investigating both normal brain functions and brain disorders. Quantitative EEG analysis enables identification of frequencies and brain activity that are activated or impaired. With studies on the structural and functional networks of the brain, the concept of the brain as a complex network has been fundamental to understand normal brain functions and the pathophysiology of various neurological disorders. Functional connectivity is a measure of neural synchrony in the brain network that refers to the statistical interdependency between neural oscillations over time. In this review, we first discuss the basic methods of EEG analysis, including preprocessing, spectral analysis, and functional-connectivity and graph-theory measures. We then review previous EEG studies of brain network characterization in several neurological disorders, including epilepsy, Alzheimer's disease, dementia with Lewy bodies, and idiopathic rapid eye movement sleep behavior disorder. Identifying the EEG-based network characteristics might improve the understanding of disease processes and aid the development of novel therapeutic approaches for various neurological disorders.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권8호
• /
• pp.443-451
• /
• 2003

Many attempts have been made for the health and lives of patients at a remote site. but little attention has been given to emergency system using wireless or other intelligent networks. In this paper, shown is a remote emergency system which can be used in an ambulance. It possibly gives a great help to the patients who may lose their lives, in other words, gives pre-hospital cure to them being sent to the hospital. Doctors or specialists are able to give a quick help which may give a new life to patients. This system deal with very important patient's data-ECG, SpO$_2$, blood pressure, biomedical signal data etc. - as other emergency system. A good performance better than other system is many but shortly spoken as follows. First, this system is user friendly system activated in windows 2000 environment. Second, MPEG4 and ECG data sent to the other station for specilists can give a pre-hospital cure to patients in advance. Third, there exist effective algorithms to operate this system. Fourth, this system has been made with software mostly, so this system can be easily embedded in IBM compatible computer. In addition to this performance, for the better and reliable system, various tests were proceeded and recursively tested. Tests were made in EV-DO wireless network and Local Area Network. This mobile-fixed remote emergency system using wireless network like EV-DO network will give a great usage to needed area.

• Advances in nano research
• /
• 제13권3호
• /
• pp.297-312
• /
• 2022

Coughing and breath shortness are common symptoms of nano (small) cell lung cancer. Smoking is main factor in causing such cancers. The cancer cells form on the soft tissues of lung. Deformation behavior and wave vibration of lung affected when cancer cells exist. Therefore, in the current work, phase velocity behavior of the small cell lung cancer as a main part of the body via an exact size-dependent theory is presented. Regarding this problem, displacement fields of small cell lung cancer are obtained using first-order shear deformation theory with five parameters. Besides, the size-dependent small cell lung cancer is modeled via nonlocal stress/strain gradient theory (NSGT). An analytical method is applied for solving the governing equations of the small cell lung cancer structure. The novelty of the current study is the consideration of the five-parameter of displacement for curved panel, and porosity as well as NSGT are employed and solved using the analytical method. For more verification, the outcomes of this reports are compared with the predictions of deep neural network (DNN) with adaptive optimization method. A thorough parametric investigation is conducted on the effect of NSGT parameters, porosity and geometry on the phase velocity behavior of the small cell lung cancer structure.

• 한국병원경영학회지
• /
• 제4권2호
• /
• pp.354-368
• /
• 1999

This research aims to compare between regression and neural network in terms of the predictive ability of the overhead costs in hospitals. For this purpose, this research uses the number of out-patients and complex medical treatments as explaining variables. Thirty-one hospitals were used for the empirical test The test result shows that the regression model has a more predictive ability than the neural network.

• 보건행정학회지
• /
• 제10권2호
• /
• pp.1-21
• /
• 2000

This study reviewde various parametic and nonparametic method for forexasting hospital closures in Korea. We compared multivariate discriminant analysis, multivartiate logistic regression, classfication and regression tree, and neural network method based on hit ratio of each model for forecasting hospital closure. Like other studies in the literture, neural metwork analysis showed highest average hit ratio. For policy and business purposes, we combined the four analytical method and constructed a foreasting model that can be easily used to predict the probabolity of hospital closure given financial information of a hospital.

• Journal of Cardiovascular Imaging
• /
• 제30권4호
• /
• pp.322-324
• /
• 2022

• 정신신체의학
• /
• 제30권2호
• /
• pp.172-178
• /
• 2022

연구목적 임상전단계의 우울증상도 삶의 질이나 자살사고와의 연관성이 높고, 자살률이 높은 우리나라의 특성상 자살과 연관성이 높은 증상을 찾기 위해 본 연구에서는 일반인구 대상으로 한 우울증상의 네트워크 구조를 밝히고자 했다. 방 법 제 7기 국민건강 영양조사 데이터를 활용했고, 19세 이상 65세 미만의 우울증 선별도구(PHQ-9) 전문항을 완료한 8,741명을 대상으로 개별 증상에 대한 Ising fit 모델을 활용하여 증상 네트워크를 찾고, 중심강도성이 높은 노드와 가중치가 높은 엣지를 확인하였다. 결 과 정신운동성 변화, 자살사고가 가장 높은 중심강도성을 보였으며 두 증상간의 연결이 가장 높은 엣지 가중치를 보였다. 자살사고는 무가치함이나 우울한 기분과도 높은 연결성을 보였다. 결 론 일반인구 집단에서도 자살사고와 관련된 증상은 우울증상 중 정신운동성 변화, 무가치함, 우울한 기분 등이 높은 연결성을 보였고, 이러한 증상들은 추후 인지행동치료 등 치료 단계에서 주요한 치료 목표가 될 수 있음을 시사한다.