Exploring the Use of Machine Learning-based Genome Wide Association Studies of Adolescent Idiopathic Scolisis

Abstract

Scoliosis is a disease marked by curvature of the spine. The most common type, adolescent idiopathic scoliosis (AIS), generally occurs right before puberty and has no known causes. According to the Scoliosis Research Society, approximately 30% of all AIS patients have some family history of scoliosis, so many researchers now are looking for a genetic component. To look for these genetic components, researchers perform what is known as a genome-wide association study, or GWAS, which the National Human Genome Research Institute defines as an “approach that involves rapidly scanning markers across the complete sets of DNA, or genomes, of many people to find genetic variations associated with a particular disease”. The results of these studies, however, have been generally inconclusive collectively. The goal of my project is to study the usage and efficacy of machine learning for GWAS in scoliosis in an effort to affirm previous results or discover new ones.