Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods.

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Abstract Text:

Baek Hwan Cho,Hwanjo Yu,Kwang-Won Kim,Tae Hyun Kim,In Young Kim,Sun I Kim,

OBJECTIVE: Diabetic nephropathy is damage to the kidney caused by diabetes mellitus. It is a common complication and a leading cause of death in people with diabetes. However, the decline in kidney function varies considerably between patients and the determinants of diabetic nephropathy have not been clearly identified. Therefore, it is very difficult to predict the onset of diabetic nephropathy accurately with simple statistical approaches such as t-test or chi(2)-test. To accurately predict the onset of diabetic nephropathy, we applied various machine learning techniques to irregular and unbalanced diabetes dataset, such as support vector machine (SVM) classification and feature selection methods. Visualization of the risk factors was another important objective to give physicians intuitive information on each patient's clinical pattern. METHODS AND MATERIALS: We collected medical data from 292 patients with diabetes and performed preprocessing to extract 184 features from the irregular data. To predict the onset of diabetic nephropathy, we compared several classification methods such as logistic regression, SVM, and SVM with a cost sensitive learning method. We also applied several feature selection methods to remove redundant features and improve the classification performance. For risk factor analysis with SVM classifiers, we have developed a new visualization system which uses a nomogram approach. RESULTS: Linear SVM classifiers combined with wrapper or embedded feature selection methods showed the best results. Among the 184 features, the classifiers selected the same 39 features and gave 0.969 of the area under the curve by receiver operating characteristics analysis. The visualization tool was able to present the effect of each feature on the decision via graphical output. CONCLUSIONS: Our proposed method can predict the onset of diabetic nephropathy about 2-3 months before the actual diagnosis with high prediction performance from an irregular and unbalanced dataset, which statistical methods such as t-test and logistic regression could not achieve. Additionally, the visualization system provides physicians with intuitive information for risk factor analysis. Therefore, physicians can benefit from the automatic early warning of each patient and visualize risk factors, which facilitate planning of effective and proper treatment strategies.

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Publishing Authors By Initials

BH Cho,H Yu,KW Kim,TH Kim,IY Kim,SI Kim,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: Artificial intelligence in medicine

VOLUME: 42

Page Numbers: 37-53

Journal Abbreviation:

ISSN: 0933-3657

DAY: 7

MONTH: 11

YEAR: 2007

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 8915031

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods.

AFFILIATION: Department of Biomedical Engineering, Hanyang University, Seoul, Republic of Korea.

Country: Netherlands

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: Artif Intell Med

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods Related Publications

• Aberrant expression of MUC3 and MUC4 membrane-associated mucins and sialyl Le(x) antigen in pancreatic intraepithelial neoplasia.
• Aberrant expression of MUC5AC and MUC6 gastric mucins and sialyl Tn antigen in intraepithelial neoplasms of the pancreas.
• Advanced capabilities for future light sources.
• Aging of the population and the subsequent increase in the mistreatment of the elderly in Korea.
• Alkali-catalyzed beta-elimination of periodate-oxidized glycans: a novel method of chemical deglycosylation of mucin gene products in paraffin embedded sections.
• Altered mucin core peptide immunoreactivity in the colon polyp-carcinoma sequence.
• Basic fibroblast growth factor-induced translocation of p21-activated kinase to the membrane is independent of phospholipase C-gamma1 in the differentiation of PC12 cells.
• Biological properties and expression of mucins in 5-fluorouracil resistant HT29 human colon cancer cells.
• Cholangiocarcinomas arising in cirrhosis and combined hepatocellular-cholangiocellular carcinomas share apomucin profiles.
• Chromosomal clustering of muscle-expressed genes in Caenorhabditis elegans.
• Drynariae Rhizoma promotes osteoblast differentiation and mineralization in MC3T3-E1 cells through regulation of bone morphogenetic protein-2, alkaline phosphatase, type I collagen and collagenase-1.
• Elderly Women's Grief in Korea.
• Expression of MUC2, MUC5AC and MUC6 apomucins in carcinoma, dysplasia and non-dysplastic epithelia of the gallbladder.
• Goblet cell-specific expression mediated by the MUC2 mucin gene promoter in the intestine of transgenic mice.
• Identification and characterization of the MUC2 (human intestinal mucin) gene 5'-flanking region: promoter activity in cultured cells.
• Immunohistochemical study of mucin carbohydrates and core proteins in hepatolithiasis and cholangiocarcinoma.
• Induction of mucin gene expression in middle ear of rats by tumor necrosis factor-alpha: potential cause for mucoid otitis media.
• Initiation of transcription of the MUC3A human intestinal mucin from a TATA-less promoter and comparison with the MUC3B amino terminus.
• MUC3 human intestinal mucin. Analysis of gene structure, the carboxyl terminus, and a novel upstream repetitive region.
• Methylation status of promoters and expression of MUC2 and MUC5AC mucins in pancreatic cancer cells.
• Molecular cloning of human intestinal mucin (MUC2) cDNA. Identification of the amino terminus and overall sequence similarity to prepro-von Willebrand factor.
• Monoclonal antibodies against partially deglycosylated colon cancer mucin that recognize Tn antigen.
• Mouse intestinal goblet cells expressing SV40 T antigen directed by the MUC2 mucin gene promoter undergo apoptosis upon migration to the villi.
• Optical design of the U7 undulator beamline at the Pohang Light Source.
• Phorbol 12-myristate 13-acetate induces alteration in mucin gene expression and biological properties of colon cancer cells.
• Phorbol 12-myristate 13-acetate up-regulates the transcription of MUC2 intestinal mucin via Ras, ERK, and NF-kappa B.
• Stent-graft placement in a traumatic internal carotid-internal jugular fistula and pseudoaneurysm.
• Stereotactic aspiration of intracerebral haematoma: significance of surgical timing and haematoma volume reduction.
• Study of the aging perception.
• The Shank family of postsynaptic density proteins interacts with and promotes synaptic accumulation of the beta PIX guanine nucleotide exchange factor for Rac1 and Cdc42.