• Genomics & Informatics
• /
• v.6 no.3
• /
• pp.142-146
• /
• 2008

In order to understand the protein functions that are related to disease, it is important to detect the correlation between amino acid mutations and disease. Many mutation studies about disease-related proteins have been carried out through molecular biology techniques, such as vector design, protein engineering, and protein crystallization. However, experimental protein mutation studies are time-consuming, be it in vivo or in vitro. We therefore performed a bioinformatic analysis of known disease-related mutations and their protein structure changes in order to analyze the correlation between mutation and disease. For this study, we selected 111 diseases that were related to 175 proteins from the PDB database and 710 mutations that were found in the protein structures. The mutations were acquired from the Human Gene Mutation Database (HGMD). We selected point mutations, excluding only insertions or deletions, for detecting structural changes. To detect a structural change by mutation, we analyzed not only the structural properties (distance of pocket and mutation, pocket size, surface size, and stability), but also the physico-chemical properties (weight, instability, isoelectric point (IEP), and GRAVY score) for the 710 mutations. We detected that the distance between the pocket and disease-related mutation lay within $20\;{\AA}$ (98.5%, 700 proteins). We found that there was no significant correlation between structural stability and disease-causing mutations or between hydrophobicity changes and critical mutations. For large-scale mutational analysis of disease-causing mutations, our bioinformatics approach, using 710 structural mutations, called "Structural Mutatomics," can help researchers to detect disease-specific mutations and to understand the biological functions of disease-related proteins.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2021

While the population of pet dogs and pet-related markets are increasing, there is no convenient and reliable tool for pet health monitoring for pet owners/caregivers. In this paper, we propose a mobile platform-based pre-diagnosis system that pet owners can use for pre-diagnosis and obtaining information on coping strategies based on their observations of the pet dog's abnormal behavior. The proposed system constructs symptom-disease association databases for 100 frequently observed diseases under veterinarian guidance. Then, we apply the possibilistic fuzzy C-means algorithm to form the "probable disease" set and the "doubtable disease" set from the database. In the experiment, we found that the proposed system found almost all diseases correctly, with an average of 4.5 input symptoms and outputs 1.5 probable and one doubtable disease on average. The utility of this system is to alert the owner's attention to the pet dog's abnormal behavior and obtain an appropriate coping strategy before consult a veterinarian.

• Journal of the Korean Society for information Management
• /
• v.33 no.1
• /
• pp.197-223
• /
• 2016

The purpose of this study is to understand information behavior of older adults with diabetes. After reviewing previous research, related factors are identified and a questionnaire was devised. The structured interview was administered to the aged 60 and over in the B hospital (N=543). Data about awareness of the disease, health literacy, information environment, information need, information seeking, information use, information service, and personal background are collected and analyzed descriptively. Relationship between variables are examined and hypotheses are tested to find factors affecting information behavior. The level of the awareness of the disease and health literacy appeared to be low. It is proved that awareness of the disease is a factor affecting information need and information use. Health literacy affects information use. There is a statistical significant difference between information need and information use by disease education and duration. There is also a statistical significant difference between information use among groups divided by information environment, sex, age, and education. Based on the results, campaign to raise disease awareness, marketing promotion about information support facilities, customized information service for older adults are suggested.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.3
• /
• pp.65-71
• /
• 2016

To reduce the expenses for development a novel drug, systems biology has been studied actively. Target prediction, a part of systems biology, contributes to finding a new purpose for FDA(Food and Drug Administration) approved drugs and development novel drugs. In this paper, we propose a classification model for predicting novel target genes based on relation between target genes and disease related genes. After collecting known target genes from TTD(Therapeutic Target Database) and disease related genes from OMIM(Online Mendelian Inheritance in Man), we analyzed the effect of target genes on disease related genes based on PPI(Protein-Protein Interactions) network. We focused on the distinguishing characteristics between known target genes and random target genes, and used the characteristics as features for building a classifier. Because our model is constructed using information about only a disease and its known targets, the model can be applied to unusual diseases without similar drugs and diseases, while existing models for finding new drug-disease associations are based on drug-drug similarity and disease-disease similarity. We validated accuracy of the model using LOOCV of ten times and the AUCs were 0.74 on Alzheimer's disease and 0.71 on Breast cancer.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.3
• /
• pp.515-521
• /
• 2004

Categorical data are mostly found in oriental medical research. The nonlinear canonical correlation analysis does not assume an interval level of measurement. In this paper, we apply nonlinear canonical correlation analysis to quantification and explain how similar sets of variables are to one another for paralysis disease data.

• Journal of Environmental Health Sciences
• /
• v.46 no.4
• /
• pp.470-479
• /
• 2020

Objectives: The Coronavirus Disease 2019 (COVID-19) pandemic has caused the death of 740,000 people around the world as of August 12, 2020. Foot-and-Mouth Disease, Avian Influenza, and African Swine Fever are serious livestock diseases. Government agencies in Korea have provided ingredient information and usage instructions for disinfectants used to counter those infectious diseases. The purpose of this study was to provide information on the chemical ingredients in disinfectant products used against COVID-19 and certain livestock diseases. Methods: We collected information from the Korean government. The Central Disaster Management Headquarters and Central Disease Control Headquarters provided information on disinfectant products used against COVID-19. The Animal and Plant Quarantine Agency of Korea provided information on efficacy-certified disinfectant products for use against selected livestock diseases. Health hazard and environmental hazard information on the ingredients in the disinfectants was collected from the Korea Occupational Safety & Health Agency's Material Safety Data Sheets, and toxicity value information was collected from United States Environmental Protection Agency's CompTox Chemicals Dashboard. Results: There were 76 COVID-19 disinfectant products in use, and the most common ingredients were benzalkonium chloride (51%), alkylbenzyl dimethyl ammonium (30%), and ethanol (3%). There were 216 livestock disease disinfectant products comprised of 89 acidic, 88 oxidic, 30 aldehydic, three alkaline, and six other products. Among the 49 active ingredients used in the disinfectants that were investigated, health and environmental hazard information was provided for many of them, but only 20 chemicals had official toxicological information. Conclusion: Since the disinfectants included numerous chemicals, an understanding of their chemical characteristics could be critical to prevent unintended human or environmental exposure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.755-762
• /
• 2022

This paper propose a clustered algorithm that possible more efficient COVID-19 disease learning prediction within clustering using context-aware attribute information. In typically, clustering of COVID-19 diseases provides to classify interrelationships within disease cluster information in the clustering process. The clustering data will be as a degrade factor if new or newly processing information during treated as contaminated factors in comparative interrelationships information. In this paper, we have shown the solving the problems and developed a clustering algorithm that can extracting disease correlation information in using K-means algorithm. According to their attributes from disease clusters using accumulated information and interrelationships clustering, the proposed algorithm analyzes the disease correlation clustering possible and centering points. The proposed algorithm showed improved adaptability to prediction accuracy of the classification management system in terms of learning as a group of multiple disease attribute information of COVID-19 through the applied simulation results.

• Child Health Nursing Research
• /
• v.5 no.3
• /
• pp.329-339
• /
• 1999

The Purpose of this study was to take the right direction and meet the requirements of newspaper function about child health through evaluation of child health information articles in newspapers. Data were collected 4 main daily newspaper by selecting child health information articles during 1 year from January 1 to December 31, 1998. The results of this study are as follows. The frequency according to health category, disease treatment(47 7%) topped followed by health maintenanceㆍpromotion(28.8%). growthㆍdevelopment(12.1%), disease Prevention(11.4%). The frequency according to WHO international disease classification, infectious disease (23.6%) take most. In evaluation area of child health information, practical usage(3.78) topped followed by accuracy(3.68), comprehensiveness(3.64), clearness (3.48), concreteness(3.33).

• 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.