Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning.

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Circadian assessment of heart failure using explainable deep learning and novel multi-parameter polar images.

BACKGROUND AND OBJECTIVE: Heart failure (HF) is a multi-faceted and life-threatening syndrome that affects more than 64.3 million people worldwide. Current gold-standard screening technique, echocardiography, neglects cardiovascular information regulated by the circadian rhythm and does not incorporate knowledge from patient profiles. In this study, we propose a novel multi-parameter approach to assess heart failure using heart rate variability (HRV) and patient clinical information. METHODS: In this approach, features from 24-hour HRV and clinical information were combined as a single polar image and fed to a 2D deep learning model to infer the HF condition. The edges of the polar image correspond to the timely variation of different features, each of which carries information on the function of the heart, and internal illustrates color-coded patient clinical information. RESULTS: Under a leave-one-subject-out cross-validation scheme and using 7,575 polar images from a multi-center cohort (American and Greek) of 303 coronary artery disease patients (median age: 58 years [50-65], median body mass index (BMI): 27.28 kg/m2 [24.91-29.41]), the model yielded mean values for the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, normalized Matthews correlation coefficient (NMCC), and accuracy of 0.883, 90.68%, 95.19%, 0.93, and 92.62%, respectively. Moreover, interpretation of the model showed proper attention to key hourly intervals and clinical information for each HF stage. CONCLUSIONS: The proposed approach could be a powerful early HF screening tool and a supplemental circadian enhancement to echocardiography which sets the basis for next-generation personalized healthcare.

Ischemia testing and revascularization in patients with monomorphic ventricular tachycardia: A relic of the past?

Testing for myocardial ischemia in patients presenting with sustained monomorphic Ventricular Tachycardia(VT) even without evidence of acute myocardial infarction is a tempting strategy that is frequently utilized in clinical practice. Monomorphic VT is mainly caused by re-entry around chronic myocardial scar and active ischemia has no role in its pathogenesis, thus making testing for ischemia futile, at least in theory. This systematic literature review sought to address the usefulness of ischemia testing (mainly coronary angiography) in patients presenting with monomorphic VT through 8 selected studies after evaluating a total of 130 published manuscripts. Particularly, we sought to unveil whether coronary angiography and possibly concomitant revascularization leads to lesser tachycardia recurrence. Our conclusion can be summarized as follows: this approach whether combined with revascularization or not, does not seem to reduce VT recurrence nor does it affect mortality in such patients. Even though most of the published literature points at this direction, validation from randomized controlled trials is imperative.

Investigating automated regression models for estimating left ventricular ejection fraction levels in heart failure patients using circadian ECG features.

Heart Failure (HF) significantly impacts approximately 26 million people worldwide, causing disruptions in the normal functioning of their hearts. The estimation of left ventricular ejection fraction (LVEF) plays a crucial role in the diagnosis, risk stratification, treatment selection, and monitoring of heart failure. However, achieving a definitive assessment is challenging, necessitating the use of echocardiography. Electrocardiogram (ECG) is a relatively simple, quick to obtain, provides continuous monitoring of patient's cardiac rhythm, and cost-effective procedure compared to echocardiography. In this study, we compare several regression models (support vector machine (SVM), extreme gradient boosting (XGBOOST), gaussian process regression (GPR) and decision tree) for the estimation of LVEF for three groups of HF patients at hourly intervals using 24-hour ECG recordings. Data from 303 HF patients with preserved, mid-range, or reduced LVEF were obtained from a multicentre cohort (American and Greek). ECG extracted features were used to train the different regression models in one-hour intervals. To enhance the best possible LVEF level estimations, hyperparameters tuning in nested loop approach was implemented (the outer loop divides the data into training and testing sets, while the inner loop further divides the training set into smaller sets for cross-validation). LVEF levels were best estimated using rational quadratic GPR and fine decision tree regression models with an average root mean square error (RMSE) of 3.83% and 3.42%, and correlation coefficients of 0.92 (p<0.01) and 0.91 (p<0.01), respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm demonstrated to be the lowest RMSE values between the actual and predicted LVEF levels. The findings could potentially lead to the development of an automated screening system for patients with coronary artery disease (CAD) by using the best measurement timings during their circadian cycles.

Management of Patients With Unexplained Syncope: Derivation and Validation of a Simplified 2-Step Diagnostic Approach.

BACKGROUND: The aim of this study was to develop a structured 2-step approach, based on noninvasive diagnostic criteria, that led to an electrophysiology study in patients with unexplained syncope. METHODS AND RESULTS: Two independent cohorts were used: the derivation cohort with 665 patients based on electronic health record data to develop our 2-step diagnostic approach, and the validation cohort based on 160 prospectively screened patients, presenting with unexplained syncope episodes. Noninvasive electrocardiographic and imaging markers and an electrophysiology study-based invasive assessment were combined. A positive diagnostic approach according to our study's prespecified criteria resulted in a decision to proceed with a permanent pacemaker/implantable cardioverter-defibrillator. The primary end point was the time until the event of recurrent syncope (syncope-free survival). Number needed to treat was calculated for patients with a positive diagnostic approach. The number of patients with unexplained syncope and borderline sinus bradycardia needed to treat was 5, and the number of patients with unexplained syncope and bundle branch block needed to treat was 3 over a mean follow-up of ≈4 years. After the structured 2-step approach, the primary outcome occurred in 14 of 82 (17.1%) with a pacemaker/implantable cardioverter-defibrillator and 19 of 57 (33%) with a negative approach, with a mean follow-up of ≈2.5 years (29.29±12.58 months, P=0.03). CONCLUSIONS: The low number needed to treat in the derivation cohort and the low percentage of syncope recurrence in the validation cohort supports the proposed 2-step electrophysiology-inclusive algorithm as a potentially low-cost, 1-day, structured tool for these patients.

Risk assessment of post-myocardial infarction patients with preserved ejection fraction using 45-min short resting Holter electrocardiographic recordings.

BACKGROUND: Risk stratification for sudden cardiac death in post-myocardial infarction (post-MI) patients remains a challenging task. Several electrocardiographic noninvasive risk factors (NIRFs) have been associated with adverse outcomes and were used to refine risk assessment. This study aimed to evaluate the performance of NIRFs extracted from 45-min short resting Holter ECG recordings (SHR), in predicting ventricular tachycardia inducibility with programmed ventricular stimulation (PVS) in post-MI patients with preserved left ventricular ejection fraction (LVEF). METHODS: We studied 99 post-MI ischemia-free patients (mean age: 60.5 ± 9.5 years, 86.9% men) with LVEF ≥40%, at least 40 days after revascularization. All the patients underwent PVS and a high-resolution SHR. The following parameters were evaluated: mean heart rate, ventricular arrhythmias (premature ventricular complexes, couplets, tachycardias), QTc duration, heart rate variability (HRV), deceleration capacity, heart rate turbulence, late potentials, and T-wave alternans. RESULTS: PVS was positive in 24 patients (24.2%). HRV, assessed by the standard deviation of normal-to-normal R-R intervals (SDNN), was significantly decreased in the positive PVS group (42 ms vs. 51 ms, p = .039). SDNN values <50 ms were also associated with PVS inducibility (OR 3.081, p = .032 in univariate analysis, and 4.588, p = .013 in multivariate analysis). No significant differences were identified for the other NIRFs. The presence of diabetes, history of ST-elevation MI (STEMI) and LVEF <50% were also important predictors of positive PVS. CONCLUSIONS: HRV assessed from SHR, combined with other noninvasive clinical and echocardiographic variables (diabetes, STEMI history, LVEF), can provide an initial, practical, and rapid screening tool for arrhythmic risk assessment in post-MI patients with preserved LVEF.

Management of Patients With Unexplained Syncope and Bundle Branch Block: Predictive Factors of Recurrent Syncope.

Syncope in patients with bundle branch block (BBB) is often due to advanced atrioventricular (AV) block. The objective of the present "real-world" study was to evaluate the optimal management in patients with unexplained syncope and BBB and to identify factors that predict the recurrence of syncope. This is a single-center observational prospective registry of 131 consecutive patients undergoing invasive electrophysiology study (EPS) for recurrent unexplained presyncope or syncope attacks and BBB. When the EPS-derived diagnosis was reached, a decision to proceed with a permanent pacemaker was offered to the patient. An implantable loop recorder was inserted in the rest of the population. A total of 131 consecutive patients with unexplained syncope and BBB (67.2% male; age 63.7 ± 16.5 years) underwent EPS during the study period. The distribution of conduction disturbance patterns was as follows: isolated left bundle branch block (LBBB): 23.7%; LBBB with first AV block: 8.4%; isolated right bundle branch block (RBBB): 10.7%; RBBB with first AV block: 8.4%; isolated left anterior/posterior fascicular block: 13%; left anterior/posterior fascicular block with first AV block: 5.3%; isolated bifascicular block: 16.8%; and bifascicular block with first AV block: 13.7%. In the multivariate analysis, the only predictors of recurrent syncope were bifascicular block (hazard ratio (HR): 4.16, 95% confidence interval (CI): 1.29, 13.41, P: 0.017) and HV interval ≥ 60 msec (HR: 3.58, 95% CI: 1.12, 11.46, P: 0.032). An EPS-based strategy identifies a subset of patients who will benefit from permanent pacing. HV interval ≥ 60 msec and the presence of a bifascicular block were strongly related to syncope recurrence.

Noninvasive electrocardiographic risk factors for sudden cardiac death in dilated ca rdiomyopathy: is ambulatory electrocardiography still relevant?

Risk stratification for sudden cardiac death in dilated cardiomyopathy is a field of constant debate, and the currently proposed criteria have been widely questioned due to their low positive and negative predictive value. In this study, we conducted a systematic review of the literature utilizing the PubMed and Cochrane library platforms, in order to gain insight about dilated cardiomyopathy and its arrhythmic risk stratification utilizing noninvasive risk markers derived mainly from 24 h electrocardiographic monitoring. The obtained articles were reviewed in order to register the various electrocardiographic noninvasive risk factors used, their prevalence, and their prognostic significance in dilated cardiomyopathy. Premature ventricular complexes, nonsustained ventricular tachycardia, late potentials on Signal averaged electrocardiography, T wave alternans, heart rate variability and deceleration capacity of the heart rate, all have both some positive and negative predictive value to identify patients in higher likelihood for ventricular arrhythmias and sudden cardiac death. Corrected QT, QT dispersion, and turbulence slope-turbulence onset of heart rate have yet to establish a predictive correlation in the literature. Although ambulatory electrocardiographic monitoring is frequently used in clinical practice in DCM patients, no single risk marker can be used for the selection of patients at high-risk for malignant ventricular arrhythmic events and sudden cardiac death who could benefit from the implantation of a defibrillator. More studies are needed in order to establish a risk score or a combination of risk factors with the purpose of selecting high-risk patients for ICD implantation in the context of primary prevention.

Safety of same-day discharge versus overnight stay strategy following cardiac device implantations: a high-volume single-centre experience.

BACKGROUND: The strategy of cardiac implantable electronic device (CIED) implantations performed as day-case admissions has gained a wider acceptance overtime; however, data on safety are still limited. This study aims to investigate the safety of a same-day discharge protocol introduced in our hospital for the postprocedural management of patients undergoing CIED implantation. METHODS: Α prospective, non-interventional, non-randomised study performed in a single high-volume implanting centre for a 16-month period (March 2020 to June 2021). At total of 821 of 965 (85.1%) patients scheduled for elective CIED implantation were considered to be eligible for inclusion in the Short-stay Device Management Protocol. These patients were compared with a historical group of 932 patients, meeting the same inclusion criteria. RESULTS: Procedure was successful in 812 patients (98.9%), committed to same-day discharge versus 921 of 932 patients (98.8%) admitted for overnight stay (p = 0.87). Overall, 90-day complication rate was comparable in both groups (4.14% vs 4.07%, p = 0.95), as was major (1.46% vs. 1.82%, p = 0.55) and minor (2.67% vs. 2.25%, p = 0.64) complication rates. The composite early post-procedural complication rates and late post-procedural complication rates were comparable among groups (0.97 vs 1.18%, p = 0.70 and 0.73% vs 0.64%, p = 0.83, respectively). Six hundred sixty-seven patients (84%) preferred the same-day discharge strategy. Finally, a reduction of 792 bed-days was recorded, resulting in possible financial Health System benefits. CONCLUSIONS: Same-day discharge is feasible and safe in the majority of patients referred for CIED implantation. Additionally, same-day discharge is preferred by patients and may reduce procedure-related costs due to significant bed-day reductions.

Association of non-invasive electrocardiographic risk factors with left ventricular systolic function in post-myocardial infarction patients with mildly reduced or preserved ejection fraction: Insights from the PRESERVE-EF study.

BACKGROUND: Electrocardiographic non-invasive risk factors (NIRFs) have an important role in the arrhythmic risk stratification of post-myocardial infarction (post-MI) patients with preserved or mildly reduced left ventricular ejection fraction (LVEF). However, their specific relation to left ventricular systolic function remains unclear. We aimed to evaluate the association between NIRFs and LVEF in the patients included in the PRESERVE-EF trial. METHODS: We studied 575 post-MI ischemia-free patients with LVEF≥40% (mean age: 57.0 ± 10.4 years, 86.2% men). The following NIRFs were evaluated: premature ventricular complexes, non-sustained ventricular tachycardia (NSVT), late potentials (LPs), prolonged QTc, increased T-wave alternans, reduced heart rate variability, and abnormal deceleration capacity with abnormal turbulence. RESULTS: There was a statistically significant relationship between LPs (Chi-squared = 4.975; p < .05), nsVT (Chi-squared = 5.749, p < .05), PVCs (r= -.136; p < .01), and the LVEF. The multivariate linear regression analysis showed that LPs (p = .001) and NSVT (p < .001) were significant predictors of the LVEF. The results of the multivariate logistic regression analysis indicated that LPs (OR: 1.76; 95% CI: 1.02-3.05; p = .004) and NSVT (OR: 2.44; 95% CI: 1.18-5.04; p = .001) were independent predictors of the mildly reduced LVEF: 40%-49% versus the preserved LVEF: ≥50%. CONCLUSION: Late potentials and NSVT are independently related to reduced LVEF while they are independent predictors of mildly reduced LVEF versus the preserved LVEF. These findings may have important implications for the arrhythmic risk stratification of post-MI patients with mildly reduced or preserved LVEF.

Arrhythmic risk stratification in ischemic, non-ischemic and hypertrophic cardiomyopathy: A two-step multifactorial, electrophysiology study inclusive approach.

Annual arrhythmic sudden cardiac death ranges from 0.6% to 4% in ischemic cardiomyopathy (ICM), 1% to 2% in non-ischemic cardiomyopathy (NICM), and 1% in hypertrophic cardiomyopathy (HCM). Towards a more effective arrhythmic risk stratification (ARS) we hereby present a two-step ARS with the usage of seven non-invasive risk factors: Late potentials presence (≥ 2/3 positive criteria), premature ventricular contractions (≥ 30/h), non-sustained ventricular tachycardia (≥ 1episode/24 h), abnormal heart rate turbulence (onset ≥ 0% and slope ≤ 2.5 ms) and reduced deceleration capacity (≤ 4.5 ms), abnormal T wave alternans (≥ 65µV), decreased heart rate variability (SDNN < 70ms), and prolonged QTc interval (> 440 ms in males and > 450 ms in females) which reflect the arrhythmogenic mechanisms for the selection of the intermediate arrhythmic risk patients in the first step. In the second step, these intermediate-risk patients undergo a programmed ventricular stimulation (PVS) for the detection of inducible, truly high-risk ICM and NICM patients, who will benefit from an implantable cardioverter defibrillator. For HCM patients, we also suggest the incorporation of the PVS either for the low HCM Risk-score patients or for the patients with one traditional risk factor in order to improve the inadequate sensitivity of the former and the low specificity of the latter.

QT interval extracted from 30-minute short resting Holter ECG recordings predicts mortality in heart failure.

BACKGROUND: Prolonged repolarization duration is a significant total mortality (TM) predictor in post-myocardial infarction patients. AIM: We examined the clinical significance of QT interval that was extracted from a Short Resting Holter ECG (SRH ECG - 30-min duration) as a TM predictor in heart failure (HF) patients. METHODS: One hundred forty-five HF patients (male = 84%, mean age = 64 ± 12 years, mean LVEF = 33 ± 10%) underwent an SRH ECG recording for 30 min. These high-resolution ECG signals were analyzed and the QT interval was calculated and corrected according to the Fridericia formula. After 42.1 months, 26 patients died. RESULTS: Univariate analysis for Deceased and Living groups: QTc:455 ± 33 ms vs 441 ± 32 ms (p = 0.04), LVEF:32 ± 10% vs 34 ± 9% (p < 0.5), Mean Heart Rate: 73 ± 11 bpm vs 69 ± 12 bpm (p = 0.2), SDNN/HRV: 45 ± 42 ms vs 41 ± 29 ms (p = 0.4), QRS: 123 ± 26 ms vs 119 ± 29 ms (p = 0.5). Multivariate Cox regression analysis with model adjusted for QTc, Mean Heart Rate, LVEF, QRS, revealed that QTc-Fridericia interval was an independent TM predictor (H.R.:1.017, 95% C.I.: 1.003-1.030, p = 0.01). The cut-off point of 490 ms (90th percentile) in the same model presented HR: 2.9 for TM (95%C.I.: 1.066-7.882, p = 0.03). Kaplan Meier curves depicted a clear difference in survival between the two patients' groups (QTc Group≥490 ms vs QTc Group <490 ms). The curve diverge was important (log-rank, p = 0.02). CONCLUSION: A fast risk stratification approach with SRH ECG recording is an efficient method for flash evaluation of mortality risk in HF patients.

Permanent pacemaker implantation in unexplained syncope patients with electrophysiology study-proven atrioventricular node disease.

OBJECTIVE: Syncope, whose cause is unknown after an initial assessment, has an uncertain prognosis. It is critical to identify patients at the highest risk who may require a pacemaker and to identify the cause of recurrent syncope to prescribe proper therapy. The aim of this study was to evaluate the effect of permanent pacing on the incidence of syncope in patients with unexplained syncope and electrophysiology study (EPS)-proven atrioventricular (AV) node disease. METHODS: This was an observational study based on a prospective registry of 236 consecutive patients (60.20 ± 18.66 years, 63.1% male, 60.04 ± 9.50 bpm) presenting with recurrent unexplained syncope attacks admitted to our hospital for invasive EPS. The decision to implant a permanent pacemaker was made in all cases by the attending physicians according to the results of the EPS. A total of 135 patients received the antibradycardia pacemaker (ABP), while 101 patients were declined. RESULTS: The mean of reported syncope episodes was 1.97 ± 1.10 (or presyncope 2.17 ± 1.50) before they were referred for a combined EP-guided diagnostic and therapeutic approach. Over a mean follow-up of approximately 4 years (49.19 ± 29.58 months), the primary outcome event (syncope) occurred in 31 of 236 patients (13.1%), and 6 of 135 (4.4%) patients in the ABP group as compared to 25 of 101 (24.8%) in the no pacemaker group (p < 0.001). CONCLUSION: Among patients with a history of unexplained syncope, a set of positivity criteria for the presence of EPS-defined AV node disease identifies a subset of patients who will benefit from permanent pacing.

His bundle pacing: A promising alternative strategy for anti-bradycardic pacing - report of a single-center experience.

His bundle pacing (HBP) is proven to be a safe and effective alternative pacing modality that, in addition, avoids pacemaker-induced cardiomyopathy (PICM) by achieving a "physiological" ventricular stimulation, via the native conduction system. Indications include various causes of bradycardia requiring anti-bradycardic pacing, inadequately controlled atrial fibrillation requiring AV node ablation and established PICM. In addition, HBP may also be used as an alternative therapy for patients with heart failure (HF) and an indication for cardiac resynchronization therapy (CRT). Available data show several advantages of HBP with regard to preservation or restoration of intra- and inter-ventricular synchronization; improvement in left ventricular ejection fraction, functional status and quality of life; decrease in atrial fibrillation incidence and improvement in HF hospitalization rates, compared with conventional pacing. Nevertheless, superiority in terms of mortality rates has not been consistently demonstrated, and the long-term efficacy and safety of HBP remain to be proven. In the present manuscript, we review the status of HBP and present our current experience with this novel pacing modality.

Noninvasive risk factors for the prediction of inducibility on programmed ventricular stimulation in post-myocardial infarction patients with an ejection fraction ≥40% at risk for sudden cardiac arrest: Insights from the PRESERVE-EF study.

BACKGROUND: In the PRESERVE-EF study, a two-step sudden cardiac death (SCD) risk stratification approach to detect post-myocardial infarction (MI) patients with left ventricle ejection fraction (LVEF) ≥40% at risk for major arrhythmic events (MAEs) was used. Seven noninvasive risk factors (NIRFs) were extracted from a 24-h ambulatory electrocardiography (AECG) and a 45-min resting recording. Patients with at least one NIRF present were referred for invasive programmed ventricular stimulation (PVS) and inducible patients received an Implantable Cardioverter - Defibrillator (ICD). METHODS: In the present study, we evaluated the performance of the NIRFs, as they were described in the PRESERVE-EF study protocol, in predicting a positive PVS. In the PRESERVE-EF study, 152 out of 575 patients underwent PVS and 41 of them were inducible. For the present analysis, data from these 152 patients were analyzed. RESULTS: Among the NIRFs examined, the presence of signal averaged ECG-late potentials (SAECG-LPs) ≥ 2/3 and non-sustained ventricular tachycardia (NSVT) ≥1 eposode/24 h cutoff points were important predictors of a positive PVS study, demonstrating in the logistic regression analysis odds ratios 2.285 (p = .027) and 2.867 (p = .006), respectively. A simple risk score based on the above cutoff points in combination with LVEF < 50% presented high sensitivity but low specificity for a positive PVS. CONCLUSION: Cutoff points of NSVT ≥ 1 episode/24 h and SAECG-LPs ≥ 2/3 in combination with a LVEF < 50% were important predictors of inducibility. However, the final decision for an ICD implantation should be based on a positive PVS, which is irreplaceable in risk stratification.