Predicting the Disease of Alzheimer With SNP Biomarkers and Clinical Data Using Data Mining Classification Approach: Decision Tree

Erdogan O., AYDIN SON Y.

25th European Medical Informatics Conference (MIE), İstanbul, Turkey, 31 August - 03 September 2014, vol.205, pp.511-515 identifier identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 205
  • Doi Number: 10.3233/978-1-61499-432-9-511
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.511-515
  • Keywords: data mining, single nucleotide polymorphism, integrating genotype and phenotype data, decision tree, alzheimers disease, GENOME-WIDE ASSOCIATION


Single Nucleotide Polymorphisms (SNPs) are the most common genomic variations where only a single nucleotide differs between individuals. Individual SNPs and SNP profiles associated with diseases can be utilized as biological markers. But there is a need to determine the SNP subsets and patients' clinical data which is informative for the diagnosis. Data mining approaches have the highest potential for extracting the knowledge from genomic datasets and selecting the representative SNPs as well as most effective and informative clinical features for the clinical diagnosis of the diseases. In this study, we have applied one of the widely used data mining classification methodology: "decision tree" for associating the SNP biomarkers and significant clinical data with the Alzheimer's disease (AD), which is the most common form of "dementia". Different tree construction parameters have been compared for the optimization, and the most accurate tree for predicting the AD is presented.