Genetic screening algorithm for inflammatory back pain

Power, Rebecca Joy (2018) Genetic screening algorithm for inflammatory back pain. Masters thesis, Memorial University of Newfoundland.

[English] PDF - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Download (4MB)

Abstract

Objective: To develop a single nucleotide polymorphism (SNP) based genetic-based algorithm among patients with low back pain to screen for axial spondyloarthritis (SpA). Methods: An 18-plex genetic assay was designed using a MassARRAY, consisting of SNPs associated with ankylosing spondylitis (AS), psoriasis, inflammatory bowel disease (IBD) and uveitis. 1172 AS cases and 848 controls have been analyzed over two cohorts. A machine learning algorithm was created using a J48/C4.5 decision tree model; the first decision was human leukocyte antigen B 27 (HLA-B*27) status. The initial algorithm was validated in an independent cohort. The discovery and validation cohorts were then combined and the final genetic-based screening algorithm was weighted. Results: The SNP based algorithm that included HLA-B*27 positivity had a precision, specificity and sensitivity of; 0.83, 0.83, and 0.80, respectively which is higher than the current HLA-B*27 based Assessment of Spondyloarthritis International Society (ASAS) classification criteria. The SNP based algorithm that included HLA-B*27 negativity had a precision, specificity and sensitivity of, 0.58, 0.32, and 0.69, respectively. Conclusions: This genetic screening algorithm is inexpensive, out performs the clinical arm of the current ASAS classification criteria and can potentially lead to earlier detection of axial SpA.

Actions (login required)

View Item