Home // International Journal On Advances in Life Sciences, volume 10, numbers 3 and 4, 2018 // View article

Analyzing the Potential Occurrence of Osteoporosis and its Correlation to Cardiovascular Disease Using Predictive Analytic

Authors:
Kae Sawada
Michael Wayne Clark
Zilong Ye
Nabil Alshurafa
Mohammad Pourhomayoun

Keywords: 1000 Genome Project; Machine Learning; Predictive Model; Genome Wide Association Study (GWAS); Data Visualization; Clustering; Classifiers; Supervised Learning.

Abstract:
In this paper, Big Data Processing was utilized to develop and validate a Predictive Analytics Model with the goal of determining the risk for an individual manifesting osteoporosis in later life. The analyzed dataset consists of the genomic information from over 2,500 individuals from all around the world. This model development leverages the novel genetic pleiotropic information, the two or more apparently unrelated phenotypes caused by a single gene. The dataset was examined for the mutations associated with osteoporosis and cardiovascular disease from the population genetics perspectives. The study also proposes the automatic histogram clustering as an effective and intuitive visualization method for high dimensional dataset. The data visualization and clustering results revealed a significant correlation between a person’s regional background and the frequency of occurrence of the 35 single nucleotide polymorphisms (SNPs). These 35 SNPs are associated with osteoporosis and/or cardiovascular disease (CVD). Distinct SNP frequency of occurrence profiles were observed for specific geographic regions. Machine learning algorithms were then applied to predict the occurrence of 7 osteoporosis-related-SNPs based on the existing CVD-related- SNPs input as an experiment. The model's validity was confirmed through a separate experimental result, utilizing a set of data obtained through Affymetrix microarray mRNA expression signal values for the specific SNP(s) in individuals with and without osteoporosis. Furthermore, these results confirmed the genetic linkage between osteoporosis and Cardiovascular related parameters such as High Density Lipoprotein (HDL) and Systolic Blood Pressure (SBP). A useful Predictive Analytics Model for determining these genetic predispositions have been produced.

Pages: 211 to 220

Copyright: Copyright (c) to authors, 2018. Used with permission.

Publication date: December 30, 2018

Published in: journal

ISSN: 1942-2660