• Journal of Nutrition and Health
• /
• v.49 no.6
• /
• pp.401-410
• /
• 2016

Purpose: Water is magnetically charged upon contact with a magnet. Although magnetic water products have been promoted since the 1930's, they have not received wide acceptance since their effectiveness is still in question; however, some have reported their therapeutic effects on the body, especially the digestive, nervous, and urinary systems. Methods: In this study, the effect of magnetized water on glycemic control of 14 diabetic mice (CB57BK/KsJ-db/db) in comparison with 10 control mice (CB57BK/KsJ-db/+(db/+)) was investigated. Seven diabetic control (DMC) mice and seven diabetic mice + magnetized water (DM+MW) were kept for 16 weeks, followed by intraperitoneal glucose tolerance test (IPGTT). Weekly blood glucose was measured from tail veins. Blood obtained from heart puncture was used for HbA1c analysis. Results: Blood glucose level showed a significant difference starting from the $10^{th}$ week of study ($496.1{\pm}10.2mg/dl$ in DMC vs. $437.9{\pm}76.9mg/dl$ in DM+MW). Blood glucose followed by IPGTT showed no significant difference between groups at 0, 30, 60, 90, and 120 min, although glucose level at 180 min was significantly reduced in DM+MW mice. Plasma insulin level in DM+MW groups was only 39.5% of that of DMC groups ($5.97{\pm}1.69ng/ml$ in DMC vs. $2.36{\pm}0.94ng/ml$ in DM+MW). Levels of HbA1c were 12.4% and 9.7% in DMC and DM+MW groups, respectively. Conclusion: These results show the promising therapeutic effect of magnetized water in regulating blood glucose homeostasis; however, long-term supplementation or mechanistic study is necessary.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Laboratory Medicine Online
• /
• v.6 no.1
• /
• pp.25-30
• /
• 2016

Background: The cell cycle-dependent enzyme thymidine kinase 1 (TK1) is known to increase during cancer cell proliferation and has been reported as a prognostic marker for various hematologic malignancies and solid tumors. This study aimed to determine the reference interval in Korean healthy controls and to evaluate the usefulness of TK1 as a biomarker for aggressive clinical behavior in B-cell lymphoma patients. Methods: We enrolled 72 previously untreated patients with B-cell lymphoma and 143 healthy controls. Serum TK1 levels were measured by chemiluminescence immunoassay ($Liaison^{(R)}$, DiaSorin, USA). We established the reference intervals in healthy controls. The diagnostic performance of serum TK1 was studied using receiver operating characteristic (ROC) analysis, and the correlation between the cutoff level for serum TK1 and clinical characteristics of B-cell lymphoma was evaluated. Results: The reference range (95th percentile) of serum TK1 in healthy controls was 5.4-21.8 U/L. There was a clear difference in TK1 levels between patients with B-cell lymphoma and healthy controls ($40.6{\pm}68.5$ vs. $11.8{\pm}4.4U/L$, P <0.001). The area under the curve of serum TK1 for the diagnosis of B-cell lymphoma was 0.73 (cutoff, 15.2 U/L; sensitivity, 59.7%; specificity, 83.2%). An increased TK1 level (${\geq}15.2U/L$) correlated with the advanced clinical stage (P <0.001), bone marrow involvement (P =0.013), international prognostic index score (P =0.001), lactate dehydrogenase level (P =0.001), low Hb level (<12 g/dL) (P =0.028), and lymphocyte count (P =0.023). Conclusions: The serum TK1 level could serve as a useful biomarker for aggressive clinical behavior in B-cell lymphoma patients.