Award Date

5-1-2020

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Fatma Nasoz

Second Committee Member

Qing Wu

Third Committee Member

Laxmi Gewali

Fourth Committee Member

Yoohwan Kim

Fifth Committee Member

Mira Han

Number of Pages

102

Abstract

Osteoporosis becomes very common problem for people after a certain age, which results in fragility fractures without any previous symptoms. One of the primary predictors of osteoporosis is bone mineral density (BMD). BMD is the mineral content of bone, at the optimal levels, that makes the bone strong enough to bear the regular load and elastic enough to handle the irregular twisting load. Two of the major parts of the bone that help to acquire such property are trabecular and cortical bone. This thesis focuses on predicting the BMDs of trabecular and cortical bone for men. For this purpose we performed Genome Wide Association Study (GWAS) for quality control and obtained new subsets of 537 and 536 Single Nucleotide Polymorphisms (SNPs) associated with trabecular and cortical BMDs. Various machine learning algorithms were used for the predictive analysis, among which linear regression (LR), support vector machine (SVM) and multi-layer perceptron (MLP) gave much better results with the newly obtained subset of SNPs, compared to the results using the 1103 and 307 SNPs associated with BMD found in the existing literature. LR gave mean squared error (MSE) of 0.000658 and coefficient of determination (r2) of 0.643479, SVM gave MSE of 0.000628 and r2 of 0.65971, and MLP gave MSE 0.000683 and r2 0.62989 for trabecular BMD with 537 SNPs. Similarly, LR, SVM, and MLP gave MSEs of 0.001109, 0.001103, and 0.00112, and r2 of 0.707548, 0.709079 and 0.703947, respectively, for cortical BMD with 536 SNPs. In both cases, SVM gave better results.

Keywords

Osteoporosis; Bone mineral density (BMD); Genome Wide Association Study (GWAS); Single Nucleotide Polymorphisms (SNPs)

Disciplines

Computer Sciences

File Format

pdf

File Size

3.1 MB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Download


Share

COinS