High-frequency electrocardiogram analysis in the ability to predict reversible perfusion defects during adenosine myocardial perfusion imaging

Heart age estimated using explainable advanced electrocardiography

Electrocardiographic (ECG) Heart Age conveying cardiovascular risk has been estimated by both Bayesian and artificial intelligence approaches. We hypothesised that explainable measures from the 10-s 12-lead ECG could successfully predict Bayesian 5-min ECG Heart Age. Advanced analysis was performed on ECGs from healthy subjects and patients with cardiovascular risk or proven heart disease. Regression models were used to predict patients’ Bayesian 5-min ECG Heart Ages from their standard, resting 10-s 12-lead ECGs. The difference between 5-min and 10-s ECG Heart Ages were analyzed, as were the differences between 10-s ECG Heart Age and the chronological age (the Heart Age Gap). In total, 2,771 subjects were included (n = 1682 healthy volunteers, n = 305 with cardiovascular risk factors, n = 784 with cardiovascular disease). Overall, 10-s Heart Age showed strong agreement with the 5-min Heart Age (R² = 0.94, p < 0.001, mean ± SD bias 0.0 ± 5.1 years). The Heart Age Gap was 0.0 ± 5.7 years in healthy individuals, 7.4 ± 7.3 years in subjects with cardiovascular risk factors (p < 0.001), and 14.3 ± 9.2 years in patients with cardiovascular disease (p < 0.001). Heart Age can be accurately estimated from a 10-s 12-lead ECG in a transparent and explainable fashion based on known ECG measures, without deep neural network-type artificial intelligence techniques. The Heart Age Gap increases markedly with cardiovascular risk and disease.

Diagnostic utility of the spatial versus individual planar QRS-T angles in cardiac disease detection

INTRODUCTION

We compared the diagnostic utility of various planar QRS-T angles to that of the spatial QRS-T angle in detecting various cardiac diseases.

MATERIALS AND METHODS

Electrocardiographic (ECG) and derived vectorcardiographic (VCG) data were analyzed from 370 patients with imaging-proven cardiac disease (coronary artery disease, hypertrophic cardiomyopathy, or left ventricular systolic dysfunction) and 210 apparently healthy controls. The areas under the curve (AUC) of the Receiver Operating Characteristic (ROC) for distinguishing cardiac health from disease for each disease condition were statistically compared for the spatial mean QRS-T angle versus the ECG-derived frontal and VCG-derived frontal, left sagittal and horizontal planar QRS-T angles.

RESULTS

The AUC ROC of the spatial mean QRS-T angle, which ranged from 0.801 ± 0.035 to 0.987 ± 0.007 depending on the specific comparison, was always significantly greater than that of the ECG frontal planar QRS-T angle (range from 0.680 ± 0.043 to 0.796 ± 0.045) and usually significantly greater than that of all other QRS-T angles for the diseases studied.

DISCUSSION

The spatial mean QRS-T angle is statistically significantly more diagnostically powerful than the ECG-derived frontal planar QRS-T angle and also generally more diagnostically powerful than all VCG-derived planar QRS-T angles in detecting cardiac disease. The ECG frontal planar QRS-T angle should not be considered an adequate diagnostic substitute for the spatial QRS-T angle.

Changes in the initial slope of the QRS in ischemic patients and normal subjects undergoing scintigraphy with dipyridamole

The effect of dipyridamole (Dp) on the linear portion of the first major deflection of the QRS in human electrocardiograms (which we refer to as Fslope) was investigated in the context of myocardial perfusion imaging (MPI), in normal subjects (NS, n=19) and in patients with cardiovascular ischemia (as manifested by a positive MPI scan, n=53). In the majority of participants, Fslope decreased (84% of 19 NS and 77% of 53 patients, p=0.69). The decrease in Fslope was more pronounced in patients with ST-T deviation as compared to those without (32.6±24.5 vs. 22.4±23.1, p=0.24), and in patients vs. NS (24.9±23.5 vs. 19.6±23.4, p=0.44). A change in Fslope is a sensitive (but not specific) measure for detecting the effect of Dp on the myocardium in the setting of scintigraphy.

Accuracy of advanced versus strictly conventional 12-lead ECG for detection and screening of coronary artery disease, left ventricular hypertrophy and left ventricular systolic dysfunction

Background

Resting conventional 12-lead ECG has low sensitivity for detection of coronary artery disease (CAD) and left ventricular hypertrophy (LVH) and low positive predictive value (PPV) for prediction of left ventricular systolic dysfunction (LVSD). We hypothesized that a ~5-min resting 12-lead advanced ECG test ("A-ECG") that combined results from both the advanced and conventional ECG could more accurately screen for these conditions than strictly conventional ECG.

Methods

Results from nearly every conventional and advanced resting ECG parameter known from the literature to have diagnostic or predictive value were first retrospectively evaluated in 418 healthy controls and 290 patients with imaging-proven CAD, LVH and/or LVSD. Each ECG parameter was examined for potential inclusion within multi-parameter A-ECG scores derived from multivariate regression models that were designed to optimally screen for disease in general or LVSD in particular. The performance of the best retrospectively-validated A-ECG scores was then compared against that of optimized pooled criteria from the strictly conventional ECG in a test set of 315 additional individuals.

Results

Compared to optimized pooled criteria from the strictly conventional ECG, a 7-parameter A-ECG score validated in the training set increased the sensitivity of resting ECG for identifying disease in the test set from 78% (72-84%) to 92% (88-96%) (P < 0.0001) while also increasing specificity from 85% (77-91%) to 94% (88-98%) (P < 0.05). In diseased patients, another 5-parameter A-ECG score increased the PPV of ECG for LVSD from 53% (41-65%) to 92% (78-98%) (P < 0.0001) without compromising related negative predictive value.

Conclusion

Resting 12-lead A-ECG scoring is more accurate than strictly conventional ECG in screening for CAD, LVH and LVSD.