Why the study?
Pre-test probability models are key for diagnosing suspected obstructive CAD, but their accuracy remains controversial.
Does a machine learning model using clinically relevant biomarkers improve the prediction of stable obstructive CAD compared to established pre-test probability models in patients with suspected CAD?
Population
1,312 patients with suspected obstructive CAD
Comparison
Eight machine learning models vs established pre-test probability models
Design
Cohort model development and internal validation study
Authors
Loading...
Should not yet change pretest pathways for suspected CAD; leaves open external validation of biomarker-ML models versus PTP scores.
Does a machine learning model using clinically relevant biomarkers improve the prediction of stable obstructive CAD compared to established pre-test probability models in patients with suspected CAD?
Machine learning models incorporating routine clinical and blood biomarkers provide higher accuracy for predicting stable obstructive CAD than traditional pre-test probability scores.
Kim et al. (2022) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: