• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.940-952
• /
• 2020

The Alzheimer's disease (AD) is a neurodegenerative disease commonly found in the elderly individuals. It is one of the most common forms of dementia; patients with AD suffer from a degradation of cognitive abilities over time. To correctly diagnose AD, compuated-aided system equipped with automatic classification algorithm is of great importance. In this paper, we propose a novel deep learning based classification algorithm that takes advantage of MRI biomarker images including brain areas of hippocampus and cerebrospinal fluid for the purpose of improving the AD classification performance. In particular, we develop a new approach that effectively applies MRI biomarker patch images as input to 3D Deep Convolution Neural Network. To integrate multiple classification results from multiple biomarker patch images, we proposed the effective confidence score fusion that combine classification scores generated from soft-max layer. Experimental results show that AD classification performance can be considerably enhanced by using our proposed approach. Compared to the conventional AD classification approach relying on entire MRI input, our proposed method can improve AD classification performance of up to 10.57% thanks to using biomarker patch images. Moreover, the proposed method can attain better or comparable AD classification performances, compared to state-of-the-art methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1331-1336
• /
• 2023

In text-based fish disease classification using machine learning, there is a problem that the input parameters of the machine learning model are too many, but due to performance problems, the input parameters cannot be arbitrarily reduced. This paper proposes a method of optimizing input parameters specialized for Paralichthys olivaceus disease classification using SHAP analysis techniques to solve this problem,. The proposed method includes data preprocessing of disease information extracted from the halibut disease questionnaire by applying the SHAP analysis technique and evaluating a machine learning model using AutoML. Through this, the performance of the input parameters of AutoML is evaluated and the optimal input parameter combination is derived. In this study, the proposed method is expected to be able to maintain the existing performance while reducing the number of input parameters required, which will contribute to enhancing the efficiency and practicality of text-based Paralichthys olivaceus disease classification.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• The Journal of the Korean dental association
• /
• v.48 no.6
• /
• pp.459-468
• /
• 2010

International Classification of Disease (ICD-10) is widely used as a crucial reference not only in the medical diagnosis of diseases but also within the health insurance system. It makes possible for medical personnel to make decisions systematically and for the people working in the health insurance or public health industries to better understand medical issues. However, this classification is often not enough or acceptable in a clinical setting. Many countries amend in their own way to make it more appropriate for their people. Korean Classification of Disease (KCD-5) was made by adding a 5 digit code for some diseases to clarify the conditions of the patients. The authors found problems of KCD-5 in temporomandibular disorders and several related medical problems. Medical treatment for these problems had not been covered even by public health insurance until 2000 in Korea. For the last decade, private insurance companies have introduced new items for reimbursement of the treatment fees the patients actually pay. The authors assumed that many patients with these medical problems encountered difficulties in the reimbursement from private insurance companies because KCD-5 did not classify these medical conditions appropriately. An overview of KCD-5 and suggestions for improvement are introduced in this study.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.80-85
• /
• 2011

Alzheimer's disease and Parkinson's disease are the most common neurodegenerative disorders. In this paper, we proposed a feature extraction method for classification of AD and PD based on micro-Raman spectra from platelet. The first step of the preprocessing is a simple smoothing followed by background elimination to the original spectra to make it easy to measure the intensity of the peaks. The last step of the preprocessing was peak alignment with the reference peak. After the inspection of the preprocessed spectra, we found that proportion of two peak intensity at 743 and $757cm^{-1}$ and peak intensity at 1248 and $1448cm^{-1}$ are the most discriminative features. Then we apply mapstd method for normalization. The method returned data with means to 0 and deviation to 1. With these three features, the classification result involving 263 spectra showed about 95.8% true classification in case of MAP(maximum a posteriori probability).

• Annals of Occupational and Environmental Medicine
• /
• v.35
• /
• pp.26.1-26.15
• /
• 2023

Background: The objective of this study is to investigate the differences in incidence rates of targeted diseases by classification of occupations among construction workers in Korea. Methods: In a subject-based cohort of the Korean Construction Worker's Cohort, we surveyed a total of 1,027 construction workers. As occupational exposure, the classification of occupations was developed using two axes: construction business and job type. To analyze disease incidence, we linked survey data with National Health Insurance Service data. Eleven target disease categories with high prevalence or estimated work-relatedness among construction workers were evaluated in our study. The average incidence rates were calculated as cases per 1,000 person-years (PY). Results: Injury, poisoning, and certain other consequences of external causes had the highest incidence rate of 344.08 per 1,000 PY, followed by disease of the musculoskeletal system and connective tissue for 208.64 and diseases of the skin and subcutaneous tissue for 197.87 in our cohort. We especially found that chronic obstructive pulmonary disease was more common in construction painters, civil engineering welders, and civil engineering frame mold carpenters, asthma in construction painters, landscape, and construction water proofers, interstitial lung diseases in construction water proofers. Conclusions: This is the first study to systematically classify complex construction occupations in order to analyze occupational diseases in Korean construction workers. There were differences in disease incidences among construction workers based on the classification of occupations. It is necessary to develop customized occupational safety and health policies for high-risk occupations for each disease in the construction industry.

• Korea Journal of Hospital Management
• /
• v.21 no.4
• /
• pp.55-62
• /
• 2016

Purposes: The industry has specialized and fragmented than in the past. As a factor of economic growth and industrialization, the number of people employed in primary industry decreased and the number of people employed in secondary and third industry continuously increased. In modern times, incidence of chronic disease is increasing according to industrial development. So, the purpose of this study was to analyze the chronic disease according to Clark's industrial classification. Methodology: Data were derived from the 2012 Korea Health Panel. The sample was made up of 7,132 adult participants aged 20 or over selected Korea Health Panel by probability sampling from Korea. Binary logistic regression analysis was conducted to examine the main factors associated with chronic disease. Findings: The significant factors associated with chronic disease were gender, age, marital status, household member, education level, insurance type, disability, BMI, and industrial classification. Female, elderly, divorced(including bereavement, missing and separation), one-person households, less than high school graduation, medical aid, disability, obese and primary industry were confirmed chronic disease increases. Practical Implications: The study finds that primary industry's prevalence of chronic disease was higher than secondary and third industry. Therefore, this study aims to management and effort of the worker who engaged in the primary industry. Policy development is required to address inequality or popularization of the differences in these factors by conducting a study to define the working conditions and socio-economic factors between industry.

• Health Policy and Management
• /
• v.2 no.1
• /
• pp.66-79
• /
• 1992

The code of the International Classification of Disease(ICD) is seriously questioned on its effectiveness in identifing an independent disease entity from similar conditions at general practitioner's offices. This study has attempted to show individual coding variations in ICD for similar ambulatory care conditions. It has been assumed that a following outpatient visit is regarded as the sane kind of visit owing to the same disease if a visit to the different source of care would be mad within an interval of less than two days. The 'D' health insurance association was selected for this analysis. The 'D' association had 153,298 members and made claims of 642,605 outpatient care in 1990. Out of the total outpatient claims, 8.6%(55,102 claims) were counted as the same disease which could meet the above assumption. Percent of conditions classified as the 10 leading causes of frequent visits which were matched accurately to the subsequent ICD diagnostic code found to be 15.8% on the average. The URI was noted for the highest concurrence rate of 20.4%. This proportion was even decreased to 11.6% on the case of chronic disease. Despite the fact that the assumption underlying the definition of the above same disease is rather rough and inappropriate, this study reveals that the code of ICD currently in use has weaknesses in seperating a certain independent disease from similar conditions at the outpatient setting. Thus, efforts need to be elaborated to meet the need of a new system of classification for conditions and diseases encountering at ambulatory care.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.209-214
• /
• 2016

The purpose of this study was to classify healty persons and Parkinson disease patients from the vocal characteristics of healty persons and the of Parkinson disease patients using Machine Learning algorithms. So, we compared the most widely used algorithms for Machine Learning such as J48 algorithm and REPTree algorithm. In order to evaluate the classification performance of the two algorithms, the results were compared with depending on vocal characteristics. The classification performance of depending on vocal characteristics show 88.72% and 84.62%. The test results showed that the J48 algorithms was superior to REPTree algorithms.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.135-142
• /
• 2022

Despite global medical advancements, many patients are misdiagnosed, and more people are dying as a result. We must now develop techniques that provide the most accurate diagnosis of heart disease based on recorded data. To help immediate and accurate diagnose of heart disease, several data mining methods are accustomed to anticipating the disease. A large amount of clinical information offered data mining strategies to uncover the hidden pattern. This paper presents, comparison between different classification techniques, we applied on the same dataset to see what is the best. In the end, we found that the Random Forest algorithm had the best results.