| Title: | Evaluation of a machine learning-based metabolic marker for coronary artery disease in the UK Biobank |
| Journal: | Atherosclerosis |
| Published: | 18 Dec 2024 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/39799755/ |
| DOI: | https://doi.org/10.1016/j.atherosclerosis.2024.119103 |
Publication 14237
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
BACKGROUND AND AIMS: An in silico quantitative score of coronary artery disease (ISCAD), built using machine learning and clinical data from electronic health records, has been shown to result in gradations of risk of subclinical atherosclerosis, coronary artery disease (CAD) sequelae, and mortality. Large-scale metabolite biomarker profiling provides increased portability and objectivity in machine learning for disease prediction and gradation. However, these models have not been fully leveraged. We evaluated a quantitative score of CAD derived from probabilities of a machine learning model trained on metabolomic data.</p>
METHODS: We developed a CAD-predictive learning model using metabolic data from 93,642 individuals from the UK Biobank (median [IQR] age, 57 [14] years; 39,796 [42 %] male; 5640 [6 %] with diagnosed CAD), and assessed its probabilities as a quantitative metabolic risk score for CAD (M-CAD; range 0 [lowest probability] to 1 [highest probability]) in participants of the UK Biobank. The relationship of M-CAD with arterial stiffness index, ejection fraction, CAD sequelae, and mortality was assessed.</p>
RESULTS: The model predicted CAD with an area under the receiver-operating-characteristic curve of 0.712. Arterial Stiffness Index increased by 0.19 and ejection fraction decreased by 0.2 % per 0.1 increase in M-CAD. Both incident and recurrent myocardial infarction increased stepwise over M-CAD quartiles (odds ratio (OR) 15.3 [4.2 %] and 12.5 [0.2 %]) in top quartiles as compared to the first quartile of incident and recurrent MI respectively). Likewise, the hazard ratio and prevalence of all-cause mortality, CVD-associated mortality, and CAD-associated mortality increased stepwise over M-CAD deciles (2.98 [14 %], 9.34 [4.3 %], 26.7 [2.7 %] in the top deciles as compared to the first decile of all-cause, CVD, and CAD mortality respectively).</p>
CONCLUSIONS: Metabolic-based machine learning can be used to build a quantitative risk score for CAD that is associated with atherosclerotic burden, CAD sequelae and mortality.</p>
16 Keywords
- Aged
- Biological Specimen Banks
- Biomarkers
- Coronary Artery Disease
- Female
- Humans
- Machine Learning
- Male
- Metabolomics
- Middle Aged
- Predictive Value of Tests
- Prognosis
- Risk Assessment
- Risk Factors
- UK Biobank
- United Kingdom
10 Authors
- Kyle Gibson
- Iain S Forrest
- Ben O Petrazzini
- Áine Duffy
- Joshua K Park
- Waqas Malick
- Robert S Rosenson
- Ghislain Rocheleau
- Daniel M Jordan
- Ron Do
Enabling scientific discoveries that improve human health