NYMC Faculty Publications
Biomarker Selection and a Prospective Metabolite-Based Machine Learning Diagnostic for Lyme Disease
Author Type(s)
Faculty
DOI
10.1038/s41598-022-05451-0
Journal Title
Scientific Reports
First Page
1478
Document Type
Article
Publication Date
1-27-2022
Department
Medicine
Abstract
We provide a pipeline for data preprocessing, biomarker selection, and classification of liquid chromatography-mass spectrometry (LCMS) serum samples to generate a prospective diagnostic test for Lyme disease. We utilize tools of machine learning (ML), e.g., sparse support vector machines (SSVM), iterative feature removal (IFR), and k-fold feature ranking to select several biomarkers and build a discriminant model for Lyme disease. We report a 98.13% test balanced success rate (BSR) of our model based on a sequestered test set of LCMS serum samples. The methodology employed is general and can be readily adapted to other LCMS, or metabolomics, data sets.
Recommended Citation
Kehoe, E. R., Fitzgerald, B. L., Graham, B., Islam, M. N., Sharma, K., Wormser, G. P., Belisle, J. T., & Kirby, M. J. (2022). Biomarker Selection and a Prospective Metabolite-Based Machine Learning Diagnostic for Lyme Disease. Scientific Reports, 12 (1), 1478. https://doi.org/10.1038/s41598-022-05451-0