• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.504-519
• /
• 2023

Heart disease is becoming the top reason of death all around the world. Diagnosing cardiac illness is a difficult endeavor that necessitates both expertise and extensive knowledge. Machine learning (ML) is becoming gradually more important in the medical field. Most of the works have concentrated on the prediction of cardiac disease, however the precision of the results is minimal, and data integrity is uncertain. To solve these difficulties, this research creates an Integrated Accurate-Secure Heart Disease Prediction (IAS) Model based on Deep Convolutional Neural Networks. Heart-related medical data is collected and pre-processed. Secondly, feature extraction is processed with two factors, from signals and acquired data, which are further trained for classification. The Deep Convolutional Neural Networks (DCNN) is used to categorize received sensor data as normal or abnormal. Furthermore, the results are safeguarded by implementing an integrity validation mechanism based on the hash algorithm. The system's performance is evaluated by comparing the proposed to existing models. The results explain that the proposed model-based cardiac disease diagnosis model surpasses previous techniques. The proposed method demonstrates that it attains accuracy of 98.5 % for the maximum amount of records, which is higher than available classifiers.

• 한국병원경영학회지
• /
• 제25권2호
• /
• pp.45-56
• /
• 2020

Purpose: The purpose of this study is to investigate medical care behaviors influencing accuracy of the payment based New diagnosis-related groups (DRG) compared to fee for service (FFS) in hospitalized patients with medical illness. Methodology: In order to estimate the difference in medical costs between New DRG and FFS depending on medical care behaviors, medical records and hospital claims data (n=4,232) were utilized, which were collected from a single public hospital during the first-half of 2018. Data were analyzed by descriptive statistics, t-test, chi-square test, and multivariate binary logistic regression. Findings: The average difference in medical costs between New DRG and FFS were KRW 506,711±13,945 with incentives and KRW -51,506±12,979 without incentives, respectively. Forty-four point two percent (44.2%, n=1,872) of total subjects were shown to have negative compensation in overall medical costs with New DRG compared to the costs with FFS. Medical care behaviors that affected on the negative compensation were the presence of severe bed sores on admission, medical consultations, death, operations, medications and laboratory or imaging tests with unit price over KRW 100,000, hospital-acquired complications or underlying comorbidities, elderly patients (≧65 years), and hospitalized for more than average inpatient days defined by New DRG (p<0.001). The difference in average medical cost between New DRG and FFS for a group with mild illness was KRW -11,900±10,544, whereas it was KRW -196,800±46,364 for a group with severe illness (p<0.0001). Practical Implications: These findings suggest that New DRG payment model without incentives may incompletely cover the variation of medical costs in real clinical practice. Therefore, policy makers need to consider that the current New DRG reimbursement should be focused and refined to improve accuracy of payment on medical care resources utilized in severe and complex medical conditions.

• 대한수의학회지
• /
• 제49권4호
• /
• pp.329-334
• /
• 2009

Aujeszky's disease (AD) is a respiratory, infectious viral illness associated with high mortality, especially in neonatal piglets and has frequently been considered an economically important disease in many endemic countries. Although AD is still occurring in a geographically defined region in Korea, little attention has been paid to the economics of AD. In this study, partial budget technique was used to develop a simulation model to measure financial losses following the disease epidemic in a swine operation utilizing stochastic or deterministic parameters from the literatures and the index case herd of AD occurred in 2005, where available and applicable. For the infected case herd with a 12500-pig, the total economic loss for this operation was estimated to be about 199 million Korean won (95% confidence interval [CI] 148,645,000-250,741,000). Given net loss due to death of a pig at sow level was 119,000 won, total loss for the case herd with 1200 sows accounted for 143 million won (95% CI 92,599,000-193,729,000). The net loss of the death of one pig at growing and fattening level resulted in loss of 46,000 won (95% CI 40,000-53,000) and 126,000 won (95% CI 122,000-131,000), respectively. Taking into account for the number of pigs raised in the case herd, total loss amounted to 8 million won (95% CI 7,167,000-9,347,000) and 12 million won (95% CI 11,959,000-12,891,000), for growers and fatteners, respectively, assuming 63% of saved feed intake when a pig dies halfway through the respective period. Under the model's assumptions, suckling pig mortality was the major factors of loss in estimating the economic consequences (approximately 71.8% of the total loss). The high economic losses of a herd infected with AD suggest that the effective and region-specific control measures should be implemented in disease endemic foci.

• 보건행정학회지
• /
• 제26권1호
• /
• pp.24-29
• /
• 2016

Background: Socio-economical status, represented by poverty, is a potent factor in predicting health status, because preventable illness and death occurs due to poverty and socio-economical situation. This study aims to provide information towards on the correlation between poverty and self-rated health in consideration of elements of health behaviors and family and friend support in Philippines. Methods: Data was collected on 15th to 28th of February 2011 by using structured questionnaire through interview method. Study area is Antipolo and Tondo in Manila, Philippines. Sample size was 1,100 but only 658 cases was analyzed due to incomplete questionnaire. Results: Results show that the poverty has direct negative influence on self-rated health, while the presence of family and friend support decreased negative influence. And through the analysis of mediated moderation model, similarly poverty has also indirect negative effect on self-rated health by health behaviors and family and friend support. Especially, regular exercise was found to be a major variable that mediates poverty and self-rated health. Conclusion: In conclusion, to improve the self-rated health state of respondents need to provide emotional support especially from family and friends. Also regular exercise should be encouraged by raising health awareness through continuous health education and promotion for the residents in order to develop health behaviors.

• 한국동물번식학회:학술대회논문집
• /
• 한국동물번식학회 2003년도 학술발표대회 발표논문초록집
• /
• pp.80-80
• /
• 2003

Huntington's disease (HD) is an autosomal dominant neurodegenerative disorder characterized by motor, cognitive, and psychiatric symptoms, accompanied by marked cell death in the striatum and cortex. Stereotaxic injection of quinolinic acid (QA) into striatum results in a degeneration of GABAergic neurons and exhibits abnormal motor behaviors typical of the illness. The objective of this study was carried out to obtain basic information about whether parthenogenetic mouse embryonic stem (PmES) cells are suitable for cell replacement therapy of HD. To establish PmES cell lines, hybrid F1 (C57BL/6xCBA/N) mouse oocytes were treated with 7% ethanol for 5 min and cytochalasin-B for 4 hr to initiate spontaneous cleavage. Thus established PmES cells were induced to differentiate using bFGF (20ng/ml) followed by selection of neuronal precursor cells for 8 days in N2 medium. After selection, cells were expanded at the presence of bFGF (20 ng/ml) for another 6 days, then a final differentiation step in N2 medium for 7 days. To establish recipient animal models of HD, young adult mice (7 weeks age ICR mice) were lesioned unilaterally with a stereotaxic injection of QA (60 nM) into the striatum and the rotational behavior of the animals was tested using apomorphine (0.1mg/kg, IP) 7 days after the induction of lesion. Animals rotating more than 120 turns per hour were selected and the differentiated PmES cells (1$\times$10$^4$cells/ul) were implanted into striatum. Four weeks after the graft, immunohistochemical studies revealed the presence of cells reactive to anti-NeuN antibody. However, only a slight improvement of motor behavior was observed. By Nissl staining, cell mass resembling tumor was found at the graft site and near cortex which may explain the slight behavioral improvement. Detailed experiment on cell viability, differentiation and migration explanted in vivo is currently being studied.

• Genomics & Informatics
• /
• 제20권1호
• /
• pp.11.1-11.20
• /
• 2022

Vibrio harveyi belongs to the Vibrio genus that causes vibriosis in marine and aquatic fish species through double-stranded DNA virus replication. In humans, around 12 Vibrio species can cause gastroenteritis (gastrointestinal illness). A large amount of virus particles can be found in the cytoplasm of infected cells, which may cause death. Despite these devastating complications, there is still no cure or vaccine for the virus. As a result, we used an immunoinformatics approach to develop a multi-epitope vaccine against most pathogenic hemolysin gene of V. harveyi. The immunodominant T- and B-cell epitopes were identified using the hemolysin protein. We developed a vaccine employing three possible epitopes: cytotoxic T-lymphocytes, helper T-lymphocytes, and linear B-lymphocyte epitopes, after thorough testing. The vaccine was developed to be antigenic, immunogenic, and non-allergenic, as well as having a better solubility. Molecular dynamics simulation revealed significant structural stiffness and binding stability. In addition, the immunological simulation generated by computer revealed that the vaccination might elicit immune reactions in the actual life after injection. Finally, using Escherichia coli K12 as a model, codon optimization yielded ideal GC content and a higher codon adaptation index value, which was then included in the cloning vector pET2+ (a). Altogether, our experiment implies that the proposed peptide vaccine might be a good option for vibriosis prophylaxis.