Graduate Thesis Or Dissertation
 

Phenotyping Degeneration of the Intervertebral Disc with Principal Component Analysis and K-Means Clustering

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/5t34ss29c

Descriptions

Attribute NameValues
Creator
Abstract
  • The human intervertebral disc (IVD) provides support for the vertebral bodies, allowing for movement and load bearing. The IVD can degenerate with age or injury, impeding function and causing chronic pain. Despite disc degeneration affecting over 90% of adults over age 50, and back pain being the leading global cause of disability, the mechanism of degeneration that often leads to back pain is still not fully understood after decades of research and progress. This study seeks to direct future research by establishing phenotypes of degeneration that correspond with unique disease etiologies. The ability to characterize discs and assign phenotypes will allow for their separate study, and potentially the development of phenotype-specific treatments. In this study a machine learning tool, principal component analysis (PCA), is utilized to reduce the dimensionality of a patient dataset consisting of metrics derived from magnetic resonance imaging (MRI), histology, immunohistochemistry, and general medical information. K-means cluster analysis is then utilized to assign phenotypes to discs based on their similarities in the latent component space. We identify three unique clusters of discs representing phenotypes of degeneration, characterized by pain, disability, and disc morphologies.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details ChenJosephS2022.pdf 2022-07-21 Public Download