ANN ARBOR, MI–Computationally generated cardiac biomarkers — morphologic variability (MV), symbolic mismatch (SM), and heart rate motifs (HRMs) — can accurately stratify the risk of cardiovascular death after acute coronary syndrome (ACS), according to a study published in the Sept. 28 issue of Science Translational Medicine.
Zeeshan Syed, Ph.D., from the University of Michigan in Ann Arbor, and colleagues investigated the utility and prognostic ability of MV, SM, and HRMs to stratify the risk of death after ACS. The biomarkers were derived from the continuous electrocardiographic data collected during the TIMI-DISPERSE2 clinical trial through machine learning and data mining methods. The biomarkers were tested in more than 4,500 participants of the Metabolic Efficiency with Ranolazine for Less Ischemia in Non-ST-Elevation Acute Coronary Syndrome-Thrombolysis in Myocardial Infarction 36 (MERLIN-TIMI36) clinical trial.
The investigators found that there was a robust correlation between all three computationally generated cardiac biomarkers and cardiovascular death over a two-year interval after ACS. The information derived from each biomarker was independent of the information in the other biomarkers, as well as the information provided by existing clinical risk scores, electrocardiographic metrics, and echocardiography. The model discrimination as well as precision and recall of prediction rules based on left ventricular ejection fraction significantly improved with the addition of MV, SM, and HRMs to existing metrics.