Unlocking the potential of microRNAs: machine learning identifies key biomarkers for myocardial infarction diagnosis
Authors' conclusion
Our study demonstrated that miRNA signatures derived from PBMCs could serve as valuable novel biomarkers for cardiovascular diseases.
Study context
- Population
- Peripheral blood mononuclear cell (PBMC) samples from individuals with myocardial infarction (MI), stable coronary artery disease (CAD) and healthy individuals, from three Gene Expression Omnibus (GEO) gene expression datasets
- Comparison
- miRNA biomarker sets (differentially expressed vs AUC-ROC-selected) with machine learning models for classifying healthy, stable CAD and MI samples
- Outcome
- Classification of stable CAD vs MI, test data
Methodological detailsintegrated bioinformatics and machine learning analysis, three combined GEO datasets, two-layer classification architecture, test set evaluation
- Integrated bioinformatics and machine learning analysis
- Three combined GEO datasets
- Two-layer classification architecture
- Test set evaluation
Performance
As reported in the abstract
AUC-ROC, best performance: SVM model trained using the biomarker set selected by AUC-ROC
0.96
Accuracy, best performance: SVM model trained using the biomarker set selected by AUC-ROC
0.94
Original publication
Unlocking the potential of microRNAs: machine learning identifies key biomarkers for myocardial infarction diagnosis. Cardiovasc Diabetol. Published 11 September 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →