• 한국빅데이터학회지
• /
• 제2권2호
• /
• pp.115-128
• /
• 2017

최근 머신러닝 방법은 높은 예측력과 함께 널리 이용되지만 머신러닝을 제대로 활용하기 위해서 데이터가 가진 한계를 통계적 기법으로 해결한다면 기존보다 더 높은 예측력을 이끌어 낼 수 있다. 본 연구에서는 Longitudinal and Imbalanced Data에서 SMOTE 방법을 활용하여 불균형 문제를 해결한 결과 예측력이 증가하는 것을 확인할 수 있었다. 추가적으로 만성폐쇄성폐질환 급성악화 관련 연구가 활발히 이루어지고 있지만 급성악화와 관련 있는 요인을 찾는 연구만 이루어지고 있어 여러 요인들에 대한 복합적인 관철과 예측모형을 통한 급성악화 예측 연구는 이루어지지 않는다. 본 연구에서는 여러 요인을 같이 살펴봤을 때 어떤 요인들이 만성폐쇄성폐질환 급성악화와 관련이 있는지 확인하고 개인 맞춤형 특정 질환 예측 모형을 구축하였다.

• The Plant Pathology Journal
• /
• 제34권3호
• /
• pp.163-170
• /
• 2018

Strawberry Fusarium wilt disease, caused by Fusarium oxysporum f. sp. fragariae, is the most devastating disease in strawberry production. The pathogen produces chlamydospores which tolerate against harsh environment, fungicide and survive for decades in soil. Development of detection and quantification techniques are regarded significantly in many soilborne pathogens to prevent damage from diseases. In this study, we improved specific-quantitative primers for F. oxysporum f. sp. fragariae to reveal correlation between the pathogen density and the disease severity. Standard curve $r^2$ value of the specific-quantitative primers for qRT-PCR and meting curve were over 0.99 and $80.5^{\circ}C$, respectively. Over pathogen $10^5cfu/g$ of soil was required to cause the disease in both lab and field conditions. With the minimum density to develop the wilt disease, the pathogen affected near 60% in nursery plantation. A biological control microbe agent and soil solarization reduced the pathogen population 2-fold and 1.5-fold in soil, respectively. The developed F. oxysporum f. sp. fragariae specific qRT-PCR protocol may contribute to evaluating soil healthiness and appropriate decision making to control the disease.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.19-30
• /
• 2021

Diabetes Mellitus (DM) is one of common chronic diseases leading to severe health complications that may cause death. The disease influences individuals, community, and the government due to the continuous monitoring, lifelong commitment, and the cost of treatment. The World Health Organization (WHO) considers Saudi Arabia as one of the top 10 countries in diabetes prevalence across the world. Since most of the medical services are provided by the government, the cost of the treatment in terms of hospitals and clinical visits and lab tests represents a real burden due to the large scale of the disease. The ability to predict the diabetic status of a patient without the laboratory tests by performing screening based on some personal features can lessen the health and economic burden caused by diabetes alone. The goal of this paper is to investigate the prediction of diabetic and prediabetic patients by considering factors other than the laboratory tests, as required by physicians in general. With the data obtained from local hospitals, medical records were processed to obtain a dataset that classified patients into three classes: diabetic, prediabetic, and non-diabetic. After applying three machine learning algorithms, we established good performance for accuracy, precision, and recall of the models on the dataset. Further analysis was performed on the data to identify important non-laboratory variables related to the patients for diabetes classification. The importance of five variables (gender, physical activity level, hypertension, BMI, and age) from the person's basic health data were investigated to find their contribution to the state of a patient being diabetic, prediabetic or normal. Our analysis presented great agreement with the risk factors of diabetes and prediabetes stated by the American Diabetes Association (ADA) and other health institutions worldwide. We conclude that by performing class-specific analysis of the disease, important factors specific to Saudi population can be identified, whose management can result in controlling the disease. We also provide some recommendations learnt from this research.

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.97-104
• /
• 2017

Location prediction has been successfully utilized to provide high quality of location-based services to customers in many applications. In its usual form, the conventional type of location prediction is to predict future locations based on user's past movement history. However, as location prediction needs are expanded into much complicated cases, it becomes necessary quite frequently to make inference on the locations that target user visited in the past. Typical cases include the identification of locations that infectious disease carriers may have visited before, and crime suspects may have dropped by on a certain day at a specific time-band. Therefore, primary goal of this study is to predict locations that users visited in the past. Information used for this purpose include user's demographic information and movement histories. Data mining classifiers such as Bayesian network, neural network, support vector machine, decision tree were adopted to analyze 6868 contextual dataset and compare classifiers' performance. Results show that general Bayesian network is the most robust classifier.

• 통합자연과학논문집
• /
• 제16권2호
• /
• pp.61-67
• /
• 2023

Human body ages differently due to environmental, genetic and pathological factors. DNA methylation patterns also differs depending on various factors such as aging and several other diseases. The aging clock model, which uses these differences to predict age, analyzes DNA methylation patterns, recognizes age-specific patterns, predicts age, and grasps the speed and degree of aging. Aging occurs in everyone and causes various problems such as deterioration of physical ability and complications. Alzheimer's disease is a disease associated with aging and the most common brain degenerative disease. This disease causes various cognitive functions disabilities such as dementia and impaired judgment to motor functions, making daily life impossible. It has been reported that the incidence and progression of this disease increase with aging, and that increased phosphorylation of Aβ and tau proteins, which are overexpressed in this disease and accelerates epigenetic aging. It has also been reported that DNA methylation is significantly increased in the hippocampus and entorhinal cortex of Alzheimer's disease patients. Therefore, we calculated the biological age using the Epi clock, a pan-tissue aging clock model, and confirmed that the epigenetic age of patients suffering from Alzheimer's disease is lower than their actual age. Also, it was confirmed to slow down aging.

• 재활복지공학회논문지
• /
• 제12권1호
• /
• pp.46-52
• /
• 2018

본 연구는 65세 이상 도시거주 노인 107명을 대상으로 일반적 특성, 만성질환 상태, 낙상 관련 의학적 변수, 균형 관련 자신감, 신체적 능력, 우울감을 평가하는 도구를 통해 낙상에 영향을 미치는 관련 주 요인을 찾고자 하였다. 또한 유의한 차이가 있는 변수들 간의 상관관계를 파악하며, 이 중 낙상을 유발하는 데 높은 영향력이 있는 변수를 도출하여 예측력을 알아보았다. 연구 결과, 낙상군에서 요실금, 발의 통증, 하지근력약화, 만성 질환수 및 복용 약물수 빈도수가 비낙상군에 비해 통계적으로 유의하게 높았다. 또한 ABC (Activities-specific Balance Confidence) 총점, BBS (Berg Balance Scale) 총점, SGDS (Short Geriatric Depression Scale) 총점, FRT(Functional Reach Test) 값에서 통계학적으로 유의한 차이가 있었다. 낙상에 영향을 주는 주요인은 ABC 총점으로 점수가 낮을수록 낙상 위험이 높아짐으로써 균형능력에 대한 자기 확신감이 낮을수록 낙상의 가능성이 높아지는 것으로 나타났으며, ABC, SDGS, BBS 척도가 결합하여 적용될 경우 낙상군과 비낙상군을 구분하는 예측력은 70.1%로 높게 나타났다.

• Nuclear Medicine and Molecular Imaging
• /
• 제41권2호
• /
• pp.102-111
• /
• 2007

Dementia is a major burden for many countries including South Korea, where life expectancy is continuously growing and the proportion of aged people is rapidly growing. Neurodegenerative disorders, such as, Alzheimer disease, dementia with Lewy bodies, frontotemporal dementia, Parkinson disease, progressive supranuclear palsy, corticobasal degeneration, Huntington disease, can cause dementia, and cerebrovascular disease also can cause dementia. Depression or hypothyroidism also can cause cognitive deficits, but they are reversible by management of underlying cause unlike the forementioned dementias. Therefore these are called pseudodementia. We are entering an era of dementia care that will be based upon the identification of potentially modifiable risk factors and early disease markers, and the application of new drugs postpone progression of dementias or target specific proteins that cause dementia. Efficient pharmacologic treatment of dementia needs not only to distinguish underlying causes of dementia but also to be installed as soon as possible. Therefore, differential diagnosis and early diagnosis of dementia are utmost importance. F-18 FDG PET is useful for clarifying dementing diseases and is also useful for early detection of the diseases. Purpose of this article is to review the current value of FDG PET for dementing diseases including differential diagnosis of dementia and prediction of evolving dementia.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• IMMUNE NETWORK
• /
• 제11권6호
• /
• pp.324-335
• /
• 2011

The human leukocyte antigen (HLA), the major histocompatibility complex (MHC) in humans has been known to reside on chromosome 6 and encodes cell-surface antigen-presenting proteins and many other proteins related to immune system function. The HLA is highly polymorphic and the most genetically variable coding loci in humans. In addition to a critical role in transplantation medicine, HLA and disease associations have been widely studied across the populations worldwide and are found to be important in prediction of disease susceptibility, resistance and of evolutionary maintenance of genetic diversity. Because recently developed molecular based HLA typing has several advantages like improved specimen stability and increased resolution of HLA types, the association between HLA alleles and a given disease could be more accurately quantified. Here, in this review, we have collected HLA association data on some autoimmune diseases, infectious diseases, cancers, drug responsiveness and other diseases with unknown etiology in Koreans and attempt to summarize some remarkable HLA alleles related with specific diseases.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권7호
• /
• pp.4157-4160
• /
• 2013

Objectives: Understanding the situation of cancer awareness which doctors give to patients might lead to prognostic prediction in cases of of colorectal cancer (CRC). Methods: Subsets of 10,779 CRC patients were used to screen the risk factors from the Cancer Registry in Pudong New Area in cancer awareness, age, TNM stage, and gender. Survival of the patients was calculated by the Kaplan-Meier method and assessed by Cox regression analysis. The views of cancer awareness in doctors and patients were surveyed by telephone or household. Results: After a median observation time of 1,616 days (ranging from 0 to 4,083 days) of 10,779 available patients, 2,596 of the 4,561 patients with cancer awareness survived, whereas 2,258 of the 5,469 patients without cancer awareness and 406 of the 749 patients without information on cancer awareness died of the disease. All-cause and cancer-specific survival were poorer for the patients without cancer awareness than those with (P < 0.001 for each, log-rank test). Cox multivariate regression analysis showed that cancer concealment cases had significantly lower cancer-specific survival (hazard ratio (HR) = 1.299; 95 % confidence interval (CI): 1.200-1.407)and all-cause survival (HR = 1.324; 95 % CI: 1.227-1.428). Furthermore, attitudes of cancer awareness between doctors and patients were significantly different (P < 0.001). Conclusion: Cancer concealment, not only late-stage tumor and age, is associated with a poor survival of CRC patients.