Search | Korea Science

서혜숙;최진욱;이홍규
- Journal of Biomedical Engineering Research
- /
- v.22 no.4
- /
- pp.369-375
- /
- 2001
The statistical regression model is one of the most frequently used clinical analysis methods. It has basic assumption of linearity, additivity and normal distribution of data. However, most of biological data in medical field are nonlinear and unevenly distributed. To overcome the discrepancy between the basic assumption of statistical model and actual biological data, we propose a new analytical method based on artificial neural network. The newly developed multilayer perceptron(MLP) is trained with 120 data set (60 normal, 60 patient). On applying test data, it shows the discrimination power of 0.76. The diabetic risk factors were also identified from the MLP neural network model and the logistic regression model. The signigicant risk factors identified by MLP model were post prandial glucose level(PP2), sex(male), fasting blood sugar(FBS) level, age, SBP, AC and WHR. Those from the regression model are sex(male), PP2, age and FBS. The combined risk factors can be identified using the MLP model. Those are total cholesterol and body weight, which is consistent with the result of other clinical studies. From this experiment we have learned that MLP can be applied to the combined risk factor analysis of biological data which can not be provided by the conventional statistical method.
PDF

Na, So-Young;Shim, Jung-Ok
- Pediatric Gastroenterology, Hepatology & Nutrition
- /
- v.15 no.1
- /
- pp.13-18
- /
- 2012
The pathogenesis of inflammatory bowel diseases is not very well understood; it is currently thought to be caused by the interaction between genetic factors, environmental factors, intestinal microbes, and immune factors. Biological agents such as anti-tumor necrosis factor (anti-TNF) are widely being used as therapeutic agents. Infliximab, a chimeric monoclonal IgG1 antibody against tumor necrosis factor, has been demonstrated to have an effect in the induction and maintenance of remission in Crohn's disease in children. The effects of biological agents, typified by anti-TNFs, in inflammatory bowel disease in children; the recent concern on the administration of biological agents in combination with immunomodulators; and 'Top-down' therapy are some of the topics covered in this review.
https://doi.org/10.5223/kjpgn.2012.15.1.13 인용 PDF KSCI

Minjeong Yeo;Dongsoo Kong
- Journal of Korean Society on Water Environment
- /
- v.39 no.4
- /
- pp.288-301
- /
- 2023
This study aims to identify benthic macroinvertebrate fauna inhabiting at the mountain valley stream (Mt. Cheonggye) in Korea and the relationship between physical environmental factors and biological indices. Benthic macroinvertebrates were collected at five locations on August 24 and October 14, 2020, and were identified as 4 phyla, 7 classes, 16 orders, 42 families, and 72 species. Dominance ranged from 0.38 to 0.59, diversity 2.81 to 3.75, richness 3.25 to 4.63, evenness 0.65 to 0.84, and %EPT (Ephemeroptera-PlecopteraTrichoptera) richness value 42% to 73%, respectively. All sites were evaluated as a very good status by mostly biological indices based on tolerance of indicator organisms in Korea. As a result of principal component analysis, biological indices are classified into species-level indices and higher cartegory-level indices according to the taxonomic level of the indicator organism considered in each index. As a result of canonical correspondence analysis, it was confirmed that current velocity was a major factor that increased species richness and classified biological indices according to taxonomic category level. Water depth was a major factor related to the community indices, and the deeper the water depth, the lower the diversity and the evenness.
https://doi.org/10.15681/KSWE.2023.39.4.288 인용 PDF