Fragmented QRS complex with visible notching on standard 12-lead electrocardiogram (ECG) is understood to represent depolarization abnormalities and to signify risk of cardiac events. Depolarization abnormalities with similar prognostic implications likely exist beyond visual recognition but no technology is presently suitable for quantification of such invisible ECG abnormalities. We present such a technology. A signal processing method projects all ECG leads of the QRS complex into optimized three perpendicular dimensions, reconstructs the ECG back from this three-dimensional projection, and quantifies the difference (QRS ‘micro’-fragmentation, QRS-μf) between the original and reconstructed signals. QRS ‘micro’-fragmentation was assessed in three different populations: cardiac patients with automatic implantable cardioverter-defibrillators, cardiac patients with severe abnormalities, and general public. The predictive value of QRS-μf for mortality was investigated both univariably and in multivariable comparisons with other risk factors including visible QRS ‘macro’-fragmentation, QRS-Mf. The analysis was made in a total of 7779 subjects of whom 504 have not survived the first 5 years of follow-up. In all three populations, QRS-μf was strongly predictive of survival (P < 0.001 univariably, and P < 0.001 to P = 0.024 in multivariable regression analyses). A similar strong association with outcome was found when dichotomizing QRS-μf prospectively at 3.5%. When QRS-μf was used in multivariable analyses, QRS-Mf and QRS duration lost their predictive value. In three populations with different clinical characteristics, QRS-μf was a powerful mortality risk factor independent of several previously established risk indices. Electrophysiologic abnormalities that contribute to increased QRS-μf values are likely responsible for the predictive power of visible QRS-Mf. Principles of QRS micro-fragmentation.

Introduction: Mortality in hemodialysis (HD) patients is high with significant proportion attributed to fatal arrhythmias. In a pilot study, we showed that intradialytic electrocardiographic (ECG) monitoring can yield stable profiles of selected repolarisation descriptors and heart rate variability (HRV) parameters. This study investigated the relationship of these ECG markers with major adverse cardiac events (MACE) and mortality.Methods: Continuous ECGs were obtained during HD and repeated five times at 2‐week intervals. The QRS‐T angle calculated as Total Cosine R to T (TCRT) and T‐wave morphology dispersion (TMD) were calculated in overlapping 10 s ECG segments. High‐ (HF) and low (LF)‐frequency components and the LF/HF ratio of HRV were calculated every 5 min. These indices were averaged during the first hour of dialysis and subsequently overall recordings in each subject.Results: All ECG parameters were available in 72 patients aged 61 ± 15, 23 (31.9%) females and 26 (36.1%) diabetics. After a median follow up of 54.8 months, 16 patients died, 20 were transplanted, and 9 suffered MACE. TCRT (in degrees) was higher and LF/HF was lower in patients who died compared to survivors (112 ± 30 vs. 73 ± 35, p = 0.000 and 0.222 ± 0.418 vs. 0.401 ± 0.274, p = 0.000, respectively) and in MACE positive compared to negative (117 ± 40 vs. 77 ± 34, p = 0.017 and 0.125 ± 0.333 vs.0.401 ± 0.274, p = 0.007 respectively). In multivariate Cox regression analysis of mortality risk adjusted for age, diabetes mellitus, and coronary artery disease, TCRT and LF/HF remained significant predictors (p < 0.05).Conclusion: QRS‐T angle and HRV may serve risk assessment in future prospective studies in HD patients.

BACKGROUND: Subtle, prognostically important ECG features may not be apparent to physicians. In the course of supervised machine learning, thousands of ECG features are identified. These are not limited to conventional ECG parameters and morphology. We aimed to investigate whether neural network–derived ECG features could be used to predict future cardiovascular disease and mortality and have phenotypic and genotypic associations. METHODS: We extracted 5120 neural network–derived ECG features from an artificial intelligence–enabled ECG model trained for 6 simple diagnoses and applied unsupervised machine learning to identify 3 phenogroups. Using the identified phenogroups, we externally validated our findings in 5 diverse cohorts from the United States, Brazil, and the United Kingdom. Data were collected between 2000 and 2023. RESULTS: In total, 1 808 584 patients were included in this study. In the derivation cohort, the 3 phenogroups had significantly different mortality profiles. After adjusting for known covariates, phenogroup B had a 20% increase in long-term mortality compared with phenogroup A (hazard ratio, 1.20 [95% CI, 1.17–1.23]; P <0.0001; phenogroup A mortality, 2.2%; phenogroup B mortality, 6.1%). In univariate analyses, we found phenogroup B had a significantly greater risk of mortality in all cohorts (log-rank P <0.01 in all 5 cohorts). Phenome-wide association study showed phenogroup B had a higher rate of future atrial fibrillation (odds ratio, 2.89; P <0.00001), ventricular tachycardia (odds ratio, 2.00; P <0.00001), ischemic heart disease (odds ratio, 1.44; P <0.00001), and cardiomyopathy (odds ratio, 2.04; P <0.00001). A single-trait genome-wide association study yielded 4 loci. SCN10A , SCN5A , and CAV1 have roles in cardiac conduction and arrhythmia. ARHGAP24 does not have a clear cardiac role and may be a novel target. CONCLUSIONS: Neural network–derived ECG features can be used to predict all-cause mortality and future cardiovascular diseases. We have identified biologically plausible and novel phenotypic and genotypic associations that describe mechanisms for the increased risk identified.

Autonomic control of heart rate is well known in adult subjects, but limited data are available on the development of the heart rate control during childhood and adolescence. Continuous 12-lead electrocardiograms were recorded in 1045 healthy children and adolescents (550 females) aged 4 to 19 years during postural manoeuvres involving repeated 10-min supine, unsupported sitting, and unsupported standing positions. In each position, heart rate was measured, and heart rate variability indices were evaluated (SDNN, RMSSD, and high (HF) and low (LF) frequency components were obtained). Quasi-normalized HF frequency components were defined as qnHF = HF/(HF + LF). These measurements were, among others, related to age using linear regressions. In supine position, heart rate decreases per year of age were significant in both sexes but lower in females than in males. In standing position, these decreases per year of age were substantially lowered. RMSSD and qnHF indices were independent of age in supine position but significantly decreased with age in sitting and standing positions. Correspondingly, LF/HF proportions showed steep increases with age in sitting and standing positions but not in the supine position. The study suggests that baseline supine parasympathetic influence shows little developmental changes during childhood and adolescence but that in young children, sympathetic branch is less responsive to vagal influence. While vagal influences modulate cardiac periods in young and older children equally, they are less able to suppress the sympathetic influence in younger children.