ECG Morphological Variability in Beat Space for Risk Stratification After Acute Coronary Syndrome

Abstract

BackgroundIdentification of patients who are at high risk of adverse cardiovascular events after an acute coronary syndrome (ACS) remains a major challenge in clinical cardiology. We hypothesized that quantifying variability in electrocardiogram (ECG) morphology may improve risk stratification post‐ACS.Methods and ResultsWe developed a new metric to quantify beat‐to‐beat morphologic changes in the ECG: morphologic variability in beat space (MVB), and compared our metric to published ECG metrics (heart rate variability [HRV], deceleration capacity [DC], T‐wave alternans, heart rate turbulence, and severe autonomic failure). We tested the ability of these metrics to identify patients at high risk of cardiovascular death (CVD) using 1082 patients (1‐year CVD rate, 4.5%) from the MERLIN‐TIMI 36 (Metabolic Efficiency with Ranolazine for Less Ischemia in Non‐ST‐Elevation Acute Coronary Syndrome—Thrombolysis in Myocardial Infarction 36) clinical trial. DC, HRV/low frequency–high frequency, and MVB were all associated with CVD (hazard ratios [HRs] from 2.1 to 2.3 [P<0.05 for all] after adjusting for the TIMI risk score [TRS], left ventricular ejection fraction [LVEF], and B‐type natriuretic peptide [BNP]). In a cohort with low‐to‐moderate TRS (N=864; 1‐year CVD rate, 2.7%), only MVB was significantly associated with CVD (HR, 3.0; P=0.01, after adjusting for LVEF and BNP).ConclusionsECG morphological variability in beat space contains prognostic information complementary to the clinical variables, LVEF and BNP, in patients with low‐to‐moderate TRS. ECG metrics could help to risk stratify patients who might not otherwise be considered at high risk of CVD post‐ACS.

Beatquency domain and machine learning improve prediction of cardiovascular death after acute coronary syndrome

“…Frequency domain HRV metrics have been shown to provide useful prognostic information after a myocardial infarction in multiple studies 2 3 4 5 6 7 and after NSTEACS 17 18 . However, though frequency HRV measures are associated with elevated risk after NSTEACS, these risk measures miss significant numbers of deaths 18 . Our results suggest that quantifying LF/HF in terms of beatquency instead of frequency improves the ability to identify high-risk patients after a NSTEACS.…”

“…Beatquency LF/HF was also obtained from the power spectrum of the heart rate time series, however, the heartbeat indices were used as the “temporal” reference. Where beats or parts of the signal were removed (as described in the previous section), the number of removed beats was estimated using the average time intervals of the heartbeats immediately adjacent to the gap 18 . As mentioned in the results section, diagnostic bands for beatquency LF/HF were based on a prior study that applied LF and HF beatquency bands to normal adults as well as those with coronary artery disease and congestive heart failure: 0.03 to 0.14 (LF band) and 0.14 to 0.40 cycles/beat (HF band) 14 .…”

“…After this was done for all 5-minute windows for that patient, we defined each feature as the 90 th percentile of the power for that frequency over all 5-minute windows. This 90 th percentile value was used in previous ECG measures, and is intended to capture the maximum variability in a particular frequency while excluding outliers 17 18 . These 50 features quantify the heart rate variability at each frequency from 0.01 to 0.50 Hz.…”

“…In this study we tested the hypothesis that beatquency applied to an established HRV measure, Low Frequency High Frequency (LF/HF, a ratio of energy in two bands) 1 will improve prediction performance for cardiovascular death post NSTEACS. We focused on frequency domain measures and LF/HF because LF/HF was the best performing HRV measure on our datasets relative to other frequency domain measures (e.g., the Standard Deviation of normal RR intervals, or SDNN) in our datasets 17 18 . Because these original frequency bands were not explicitly selected for optimal risk stratification, we further used machine learning to discover the frequency and beatquency bands most useful in predicting cardiovascular death post NSTEACS.…”

Ranolazine Preserves and Improves Left Ventricular Ejection Fraction and Autonomic Measures When Added to Guideline-Driven Therapy in Chronic Heart Failure

“…Autonomic (P&S and HRV) measures have been documented to be associated with LVEF and cardiovascular risk ( 32 ). Table VI presents the P&S and LVEF data without regard to clinical outcomes.…”