Automatic SVM classification of sudden cardiac death and pump failure death from autonomic and repolarization ECG markers

Artificial Intelligence Applied to Electrical and Non-Invasive Hemodynamic Markers in Elderly Decompensated Chronic Heart Failure Patients

OBJECTIVES

The first aim of this study was to assess the predictive power of Tend interval (Te) and non-invasive hemodynamic markers, based on bioimpedance in decompensated chronic heart failure (CHF). The second one was to verify the possible differences in repolarization and hemodynamic data between CHF patients grouped by level of left ventricular ejection fraction (LVEF). Finally, we wanted to check if repolarization and hemodynamic data changed with clinical improvement or worsening in CHF patients.

METHODS

Two hundred and forty-three decompensated CHF patients were studied by 5 min ECG recordings to determine the mean and standard deviation (TeSD) of Te (first study). In a subgroup of 129 patients (second study), non-invasive hemodynamic and repolarization data were recorded for further evaluation.

RESULTS

Total in-hospital and cardiovascular mortality rates were respectively 19 and 9%. Te was higher in the deceased than in surviving subjects (Te: 120 ± 28 vs. 100 ± 25 ms) and multivariable logistic regression analysis reported that Te was related to an increase of total (χ2: 35.45, odds ratio: 1.03, 95% confidence limit: 1.02-1.05, p < 0.001) and cardiovascular mortality (χ2: 32.58, odds ratio: 1.04, 95% confidence limit: 1.02-1.06, p < 0.001). Subjects with heart failure with reduced ejection fraction (HFrEF) reported higher levels of repolarization and lower non-invasive systolic hemodynamic data in comparison to those with preserved ejection fraction (HFpEF). In the subgroup, patients with the NT-proBNP reduction after therapy showed a lower rate of Te, heart rate, blood pressures, contractility index, and left ventricular ejection time in comparison with the patients without NT-proBNP reduction.

CONCLUSION

Electrical signals from ECG and bioimpedance were capable of monitoring the patients with advanced decompensated CHF. These simple, inexpensive, non-invasive, easily repeatable, and transmissible markers could represent a tool to remotely monitor and to intercept the possible worsening of these patients early by machine learning and artificial intelligence tools.

Short-term effects of transcutaneous auricular vagus nerve stimulation on T-wave alternans in people with focal epilepsy - An exploratory pilot study

High levels of T-wave alternans (TWA) are linked to an increased risk of sudden cardiac death. People with epilepsy display elevated TWA levels that are decreased by chronic vagus nerve stimulation via implanted devices after 2-4 weeks or later. Our objective was to explore short-term effects of transcutaneous auricular vagus nerve stimulation (tVNS) on TWA. Five patients (3 female) with focal epilepsy undergoing video-EEG monitoring were included. TWA levels were determined using a one-channel modified lead I ECG via an open-source TWA-algorithm on two consecutive days, 1 h before, during and after tVNS via the left auricle. Data are given as mean ± SE. Mean TWA at baseline was 3.8 ± 0.4 µV and 3.0 ± 0.6 µV during stimulation on day 2. Stimulations on the second day were associated with TWA reductions by 22 ± 13 % that exceeded stimulation effects on the first day relative to baseline (p < 0.05). Linear mixed-models revealed effects of both stimulation (p < 0.05) and stimulation number (p < 0.005). Normalized TWA showed reproducible peak reductions at both days within 35 min after the initiation of tVNS (p < 0.05). Our observations suggest that tVNS has short-term effects on TWA, supporting the notion that vagus nerve stimulation has a beneficial impact on electrical cardiac properties.

Machine learning risk estimation and prediction of death in continuing care facilities using administrative data

In this study, we aimed to identify the factors that were associated with mortality among continuing care residents in Alberta, during the coronavirus disease 2019 (COVID-19) pandemic. We achieved this by leveraging and linking various administrative datasets together. Then, we examined pre-processing methods in terms of prediction performance. Finally, we developed several machine learning models and compared the results of these models in terms of performance. We conducted a retrospective cohort study of all continuing care residents in Alberta, Canada, from March 1, 2020, to March 31, 2021. We used a univariable and a multivariable logistic regression (LR) model to identify predictive factors of 60-day all-cause mortality by estimating odds ratios (ORs) with a 95% confidence interval. To determine the best sensitivity-specificity cut-off point, the Youden index was employed. We developed several machine learning models to determine the best model regarding performance. In this cohort study, increased age, male sex, symptoms, previous admissions, and some specific comorbidities were associated with increased mortality. Machine learning and pre-processing approaches offer a potentially valuable method for improving risk prediction for mortality, but more work is needed to show improvement beyond standard risk factors.

Artificial Intelligence in Ventricular Arrhythmias and Sudden Death

Sudden cardiac arrest due to lethal ventricular arrhythmias is a major cause of mortality worldwide and results in more years of potential life lost than any individual cancer. Most of these sudden cardiac arrest events occur unexpectedly in individuals who have not been identified as high-risk due to the inadequacy of current risk stratification tools. Artificial intelligence tools are increasingly being used to solve complex problems and are poised to help with this major unmet need in the field of clinical electrophysiology. By leveraging large and detailed datasets, artificial intelligence-based prediction models have the potential to enhance the risk stratification of lethal ventricular arrhythmias. This review presents a synthesis of the published literature and a discussion of future directions in this field.

Differential disease diagnoses of epistaxis based on dynamic uncertain causality graph

PURPOSE

Epistaxis is a common symptom and can be caused by various diseases, including nasal diseases, systemic diseases, etc. Many misdiagnosis and missed diagnosis of epistaxis are caused by lack of clinical knowledge and experience, especially some interns and the clinicans in primary hospitals. To help inexperienced clinicans improve their diagnostic accuracies of epistaxis, a computer-aided diagnostic system based on Dynamic Uncertain Causality Graph (DUCG) was designed in this study.

METHODS

We build a visual epistaxis knowledge base based on medical experts' knowledge and experience. The knowledge base intuitively expresses the causal relationship among diseases, risk factors, symptoms, signs, laboratory checks, and image examinations. The DUCG inference algorithm well addresses the patients' clinical information with the knowledge base to deduce the currently suspected diseases and calculate the probability of each suspected disease.

RESULT

The model can differentially diagnose 24 diseases with epistaxis as the chief complaint. A third-party verification was performed, and the total diagnostic precision was 97.81%. In addition, the DUCG-based diagnostic model was applied in Jiaozhou city and Zhongxian county, China, covering hundreds of primary hospitals and clinics. So far, the clinicians using the model have all agreed with the diagnostic results. The 432 real-world application cases show that this model is good for the differential diagnoses of epistaxis.

CONCLUSION

The results show that the DUCG-based epistaxis diagnosis model has high diagnostic accuracy. It can assist primary clinicians in completing the differential diagnosis of epistaxis and can be accepted by clinicians.

Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studies

BACKGROUND

Ventricular arrhythmia (VA) precipitating sudden cardiac arrest (SCD) is among the most frequent causes of death and pose a high burden on public health systems worldwide. The increasing availability of electrophysiological signals collected through conventional methods (e.g. electrocardiography (ECG)) and digital health technologies (e.g. wearable devices) in combination with novel predictive analytics using machine learning (ML) and deep learning (DL) hold potential for personalised predictions of arrhythmic events.

METHODS

This systematic review and exploratory meta-analysis assesses the state-of-the-art of ML/DL models of electrophysiological signals for personalised prediction of malignant VA or SCD, and studies potential causes of bias (PROSPERO, reference: CRD42021283464). Five electronic databases were searched to identify eligible studies. Pooled estimates of the diagnostic odds ratio (DOR) and summary area under the curve (AUROC) were calculated. Meta-analyses were performed separately for studies using publicly available, ad-hoc datasets, versus targeted clinical data acquisition. Studies were scored on risk of bias by the PROBAST tool.

FINDINGS

2194 studies were identified of which 46 were included in the systematic review and 32 in the meta-analysis. Pooling of individual models demonstrated a summary AUROC of 0.856 (95% CI 0.755-0.909) for short-term (time-to-event up to 72 h) prediction and AUROC of 0.876 (95% CI 0.642-0.980) for long-term prediction (time-to-event up to years). While models developed on ad-hoc sets had higher pooled performance (AUROC 0.919, 95% CI 0.867-0.952), they had a high risk of bias related to the re-use and overlap of small ad-hoc datasets, choices of ML tool and a lack of external model validation.

INTERPRETATION

ML and DL models appear to accurately predict malignant VA and SCD. However, wide heterogeneity between studies, in part due to small ad-hoc datasets and choice of ML model, may reduce the ability to generalise and should be addressed in future studies.

FUNDING

This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).

Similarity Changes Analysis for Heart Rate Fluctuation Regularity as a New Screening Method for Congestive Heart Failure

Congestive heart failure (CHF) is a chronic cardiovascular condition associated with dysfunction of the autonomic nervous system (ANS). Heart rate variability (HRV) has been widely used to assess ANS. This paper proposes a new HRV analysis method, which uses information-based similarity (IBS) transformation and fuzzy approximate entropy (fApEn) algorithm to obtain the fApEn_IBS index, which is used to observe the complexity of autonomic fluctuations in CHF within 24 h. We used 98 ECG records (54 health records and 44 CHF records) from the PhysioNet database. The fApEn_IBS index was statistically significant between the control and CHF groups (p < 0.001). Compared with the classical indices low-to-high frequency power ratio (LF/HF) and IBS, the fApEn_IBS index further utilizes the changes in the rhythm of heart rate (HR) fluctuations between RR intervals to fully extract relevant information between adjacent time intervals and significantly improves the performance of CHF screening. The CHF classification accuracy of fApEn_IBS was 84.69%, higher than LF/HF (77.55%) and IBS (83.67%). Moreover, the combination of IBS, fApEn_IBS, and LF/HF reached the highest CHF screening accuracy (98.98%) with the random forest (RF) classifier, indicating that the IBS and LF/HF had good complementarity. Therefore, fApEn_IBS effusively reflects the complexity of autonomic nerves in CHF and is a valuable CHF assessment tool.

Prediction of Drug-Induced Long QT Syndrome Using Machine Learning Applied to Harmonized Electronic Health Record Data

BACKGROUND

Drug-induced QT prolongation is a potentially preventable cause of morbidity and mortality, however there are no widespread clinical tools utilized to predict which individuals are at greatest risk. Machine learning (ML) algorithms may provide a method for identifying these individuals, and could be automated to directly alert providers in real time.

OBJECTIVE

This study applies ML techniques to electronic health record (EHR) data to identify an integrated risk-prediction model that can be deployed to predict risk of drug-induced QT prolongation.

METHODS

We examined harmonized data from the UCHealth EHR and identified inpatients who had received a medication known to prolong the QT interval. Using a binary outcome of the development of a QTc interval >500 ms within 24 hours of medication initiation or no ECG with a QTc interval >500 ms, we compared multiple machine learning methods by classification accuracy and performed calibration and rescaling of the final model.

RESULTS

We identified 35,639 inpatients who received a known QT-prolonging medication and an ECG performed within 24 hours of administration. Of those, 4,558 patients developed a QTc > 500 ms and 31,081 patients did not. A deep neural network with random oversampling of controls was found to provide superior classification accuracy (F1 score 0.404; AUC 0.71) for the development of a long QT interval compared with other methods. The optimal cutpoint for prediction was determined and was reasonably accurate (sensitivity 71%; specificity 73%).

CONCLUSIONS

We found that deep neural networks applied to EHR data provide reasonable prediction of which individuals are most susceptible to drug-induced QT prolongation. Future studies are needed to validate this model in novel EHRs and within the physician order entry system to assess the ability to improve patient safety.

Machine Learned Cellular Phenotypes in Cardiomyopathy Predict Sudden Death

RATIONALE

Susceptibility to VT/VF (ventricular tachycardia/fibrillation) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside.

OBJECTIVE

To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes.

METHODS AND RESULTS

We recorded 5706 ventricular MAPs in 42 patients with coronary artery disease and left ventricular ejection fraction ≤40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines and convolutional neural networks were trained to 2 end points: (1) sustained VT/VF or (2) mortality at 3 years. Support vector machines provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each end point. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI, 0.76-1.00) and 0.91 for mortality (95% CI, 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained support vector machine revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium-calcium exchanger as predominant phenotypes for VT/VF.

CONCLUSIONS

Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.

Feature rearrangement based deep learning system for predicting heart failure mortality

BACKGROUND AND OBJECTIVE

Heart Failure is a clinical syndrome commonly caused by any structural or functional impairment. Fast and accurate mortality prediction for Heart Failure is essential to improve the health care of patients and prevent them from death. However, due to the imbalance problem and poor feature representation in Heart Failure data, mortality prediction of Heart Failure is difficult with some simple models. To handle these problems, this study is focused on proposing a fast and accurate Heart Failure mortality prediction framework.

METHODS

This paper proposes a feature rearrangement based deep learning system for heart failure mortality prediction. The proposed framework improves the performance of predicting heart failure mortality by handling imbalance problem and achieving better feature representation. This paper also proposes a method named Feature rearrangement based convolutional layer, which demonstrates that the order of the input features is essential for the convolutional network.

RESULTS

The proposed system is experimentally evaluated on real-world Heart Failure data collected from the EHR system of Shanghai Shuguang Hospital, where 10,198 in-patients records are extracted between March 2009 and April 2016. Internal comparison results illustrate that the proposed framework achieves the best performance for Heart Failure mortality prediction. Extensive experimental results compared with other machine learning methods demonstrate that the proposed method has the highest average accuracy and area under the curve while predicting the three goals of in-hospital mortality, 30-day mortality, and 1-year mortality. Finally, top 12 essential clinical features are mined with their chi-square scores, which can help to assist clinicians in the treatment and research of heart failure.

CONCLUSIONS

The proposed method successfully predict different target in three observation windows. Feature rearrangement based convolutional layer and Focal loss are employed into the proposed framework, which helps promote the prediction accuracy of Heart Failure death. The proposed method is fast and accurate for predicting heart failure mortality, especially for imbalance situation. This paper also provide a reasonable pipeline to model EHRs data and handle imbalance problem in medical data.

Common Genetic Variants Modulate the Electrocardiographic Tpeak-to-Tend Interval

Sudden cardiac death is responsible for half of all deaths from cardiovascular disease. The analysis of the electrophysiological substrate for arrhythmias is crucial for optimal risk stratification. A prolonged T-peak-to-Tend (Tpe) interval on the electrocardiogram is an independent predictor of increased arrhythmic risk, and Tpe changes with heart rate are even stronger predictors. However, our understanding of the electrophysiological mechanisms supporting these risk factors is limited. We conducted genome-wide association studies (GWASs) for resting Tpe and Tpe response to exercise and recovery in ∼30,000 individuals, followed by replication in independent samples (∼42,000 for resting Tpe and ∼22,000 for Tpe response to exercise and recovery), all from UK Biobank. Fifteen and one single-nucleotide variants for resting Tpe and Tpe response to exercise, respectively, were formally replicated. In a full dataset GWAS, 13 further loci for resting Tpe, 1 for Tpe response to exercise and 1 for Tpe response to exercise were genome-wide significant (p ≤ 5 × 10-8). Sex-specific analyses indicated seven additional loci. In total, we identify 32 loci for resting Tpe, 3 for Tpe response to exercise and 3 for Tpe response to recovery modulating ventricular repolarization, as well as cardiac conduction and contraction. Our findings shed light on the genetic basis of resting Tpe and Tpe response to exercise and recovery, unveiling plausible candidate genes and biological mechanisms underlying ventricular excitability.

Assessment of a Machine Learning Model Applied to Harmonized Electronic Health Record Data for the Prediction of Incident Atrial Fibrillation

IMPORTANCE

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and its early detection could lead to significant improvements in outcomes through the appropriate prescription of anticoagulation medication. Although a variety of methods exist for screening for AF, a targeted approach, which requires an efficient method for identifying patients at risk, would be preferred.

OBJECTIVE

To examine machine learning approaches applied to electronic health record data that have been harmonized to the Observational Medical Outcomes Partnership Common Data Model for identifying risk of AF.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study used data from 2 252 219 individuals cared for in the UCHealth hospital system, which comprises 3 large hospitals in Colorado, from January 1, 2011, to October 1, 2018. Initial analysis was performed in December 2018; follow-up analysis was performed in July 2019.

EXPOSURES

All Observational Medical Outcomes Partnership Common Data Model-harmonized electronic health record features, including diagnoses, procedures, medications, age, and sex.

MAIN OUTCOMES AND MEASURES

Classification of incident AF in designated 6-month intervals, adjudicated retrospectively, based on area under the receiver operating characteristic curve and F1 statistic.

RESULTS

Of 2 252 219 individuals (1 225 533 [54.4%] women; mean [SD] age, 42.9 [22.3] years), 28 036 (1.2%) developed incident AF during a designated 6-month interval. The machine learning model that used the 200 most common electronic health record features, including age and sex, and random oversampling with a single-layer, fully connected neural network provided the optimal prediction of 6-month incident AF, with an area under the receiver operating characteristic curve of 0.800 and an F1 score of 0.110. This model performed only slightly better than a more basic logistic regression model composed of known clinical risk factors for AF, which had an area under the receiver operating characteristic curve of 0.794 and an F1 score of 0.079.

CONCLUSIONS AND RELEVANCE

Machine learning approaches to electronic health record data offer a promising method for improving risk prediction for incident AF, but more work is needed to show improvement beyond standard risk factors.

Risk stratification for cardiac mortality using electrocardiographic markers based on 24-hour Holter recordings: the JANIES-SHD study

BACKGROUND

Recent guidelines have stated that left ventricular ejection fraction (LVEF) is the gold standard marker for identifying patients at risk for cardiac mortality. However, little information is present regarding electrocardiographic (ECG) markers. This study aimed to assess ECG markers for predicting mortality or serious arrhythmia in patients with structural heart disease (SHD).

METHODS

In total, 1829 patients were enrolled into the Japanese Multicenter Observational Prospective Study (JANIES study). In this study, we analyzed data of 719 patients (569 men, age 64 ± 13 years) with SHD including mainly ischemic heart disease (65.8%). As ECG markers based on 24-hour Holter recordings, nonsustained ventricular tachycardia (NSVT), ventricular late potentials, and heart rate turbulence (HRT) were assessed. The primary endpoint was all-cause mortality, and the secondary endpoint was fatal arrhythmic events.

RESULTS

During a mean follow-up of 21 ± 11 months, all-cause mortality was eventually observed in 39 patients (5.4%). Among those patients, 32 patients (82%) suffered from cardiac causes such as heart failure and arrhythmia. Multivariate Cox regression analysis showed that after adjustment for age and LVEF, documented NSVT [hazard ratio = 2.46, 95% confidence interval (CI): 1.16-5.18, p = 0.02] and abnormal HRT (hazard ratio = 2.40, 95% CI: 1.16-4.93, p = 0.02) were significantly associated with the primary endpoint. These two ECG markers also had significant predictive values with the secondary endpoint. The combined assessment of two ECG markers improved predictive accuracy.

CONCLUSION

This study demonstrated that combined assessment of documented NSVT and abnormal HRT based on 24-hour Holter ECG recordings are recommended for predicting future serious events in this population.

HEARTEN KMS - A knowledge management system targeting the management of patients with heart failure

The aim of this work is to present the HEARTEN Knowledge Management System, one of the core modules of the HEARTEN platform. The HEARTEN platform is an mHealth collaborative environment enabling the Heart Failure patients to self-manage the disease and remain adherent, while allowing the other ecosystem actors (healthcare professionals, caregivers, nutritionists, physical activity experts, psychologists) to monitor the patient's health progress and offer personalized, predictive and preventive disease management. The HEARTEN Knowledge Management System is a tool which provides multiple functionalities to the ecosystem actors for the assessment of the patient's condition, the estimation of the patient's adherence, the prediction of potential adverse events, the calculation of Heart Failure related scores, the extraction of statistics, the association of patient clinical and non-clinical data and the provision of alerts and suggestions. The innovation of this tool lays in the analysis of multi-parametric personal data coming from different sources, including for the first time breath and saliva biomarkers, and the use of machine learning techniques. The HEARTEN Knowledge Management System consists of nine modules. The accuracy of the KMS modules ranges from 78% to 95% depending on the module/functionality.

New Concepts in Sudden Cardiac Arrest to Address an Intractable Epidemic: JACC State-of-the-Art Review

Sudden cardiac arrest (SCA) is one of the largest causes of mortality globally, with an out-of-hospital survival below 10% despite intense research. This document outlines challenges in addressing the epidemic of SCA, along the framework of respond, understand and predict, and prevent. Response could be improved by technology-assisted orchestration of community responder systems, access to automated external defibrillators, and innovations to match resuscitation resources to victims in place and time. Efforts to understand and predict SCA may be enhanced by refining taxonomy along phenotypical and pathophysiological "axes of risk," extending beyond cardiovascular pathology to identify less heterogeneous cohorts, facilitated by open-data platforms and analytics including machine learning to integrate discoveries across disciplines. Prevention of SCA must integrate these concepts, recognizing that all members of society are stakeholders. Ultimately, solutions to the public health challenge of SCA will require greater awareness, societal debate and focused public policy.

Sudden cardiac death and pump failure death prediction in chronic heart failure by combining ECG and clinical markers in an integrated risk model

Background

Sudden cardiac death (SCD) and pump failure death (PFD) are common endpoints in chronic heart failure (CHF) patients, but prevention strategies are different. Currently used tools to specifically predict these endpoints are limited. We developed risk models to specifically assess SCD and PFD risk in CHF by combining ECG markers and clinical variables.

Methods

The relation of clinical and ECG markers with SCD and PFD risk was assessed in 597 patients enrolled in the MUSIC (MUerte Súbita en Insuficiencia Cardiaca) study. ECG indices included: turbulence slope (TS), reflecting autonomic dysfunction; T-wave alternans (TWA), reflecting ventricular repolarization instability; and T-peak-to-end restitution (Δα^Tpe) and T-wave morphology restitution (TMR), both reflecting changes in dispersion of repolarization due to heart rate changes. Standard clinical indices were also included.

Results

The indices with the greatest SCD prognostic impact were gender, New York Heart Association (NYHA) class, left ventricular ejection fraction, TWA, Δα^Tpe and TMR. For PFD, the indices were diabetes, NYHA class, Δα^Tpe and TS. Using a model with only clinical variables, the hazard ratios (HRs) for SCD and PFD for patients in the high-risk group (fifth quintile of risk score) with respect to patients in the low-risk group (first and second quintiles of risk score) were both greater than 4. HRs for SCD and PFD increased to 9 and 11 when using a model including only ECG markers, and to 14 and 13, when combining clinical and ECG markers.

Conclusion

The inclusion of ECG markers capturing complementary pro-arrhythmic and pump failure mechanisms into risk models based only on standard clinical variables substantially improves prediction of SCD and PFD in CHF patients.

T-Wave Morphology Restitution Predicts Sudden Cardiac Death in Patients With Chronic Heart Failure

BACKGROUND

Patients with chronic heart failure are at high risk of sudden cardiac death (SCD). Increased dispersion of repolarization restitution has been associated with SCD, and we hypothesize that this should be reflected in the morphology of the T-wave and its variations with heart rate. The aim of this study is to propose an electrocardiogram (ECG)-based index characterizing T-wave morphology restitution (TMR), and to assess its association with SCD risk in a population of chronic heart failure patients.

METHODS AND RESULTS

Holter ECGs from 651 ambulatory patients with chronic heart failure from the MUSIC (MUerte Súbita en Insuficiencia Cardiaca) study were available for the analysis. TMR was quantified by measuring the morphological variation of the T-wave per RR increment using time-warping metrics, and its predictive power was compared to that of clinical variables such as the left ventricular ejection fraction and other ECG-derived indices, such as T-wave alternans and heart rate variability. TMR was significantly higher in SCD victims than in the rest of patients (median 0.046 versus 0.039, P<0.001). When TMR was dichotomized at TMR=0.040, the SCD rate was significantly higher in the TMR≥0.040 group (P<0.001). Cox analysis revealed that TMR≥0.040 was strongly associated with SCD, with a hazard ratio of 3.27 (P<0.001), independently of clinical and ECG-derived variables. No association was found between TMR and pump failure death.

CONCLUSIONS

This study shows that TMR is specifically associated with SCD in a population of chronic heart failure patients, and it is a better predictor than clinical and ECG-derived variables.

Heart Rate Turbulence Is a Powerful Predictor of Cardiac Death and Ventricular Arrhythmias in Postmyocardial Infarction and Heart Failure Patients: A Systematic Review and Meta-Analysis

BACKGROUND

Heart rate turbulence (HRT) has been proposed as a candidate marker of altered autonomic tone, and some studies showed its prognostic value for both cardiac death (CD) and sudden death. Nevertheless, HRT is not currently used in the clinical practice.

METHODS AND RESULTS

We performed a systematic review and meta-analysis of the predictive value of HRT for the end points of total mortality, CD, and fatal and nonfatal ventricular arrhythmias in postacute myocardial infarction and heart failure patients. MEDLINE and The Cochrane Library databases were systematically searched to identify studies, which analyzed the predictive value of abnormal HRT for the defined end points. Twenty studies (25 cohorts: 12 832 patients) were identified by the systematic review, and 15 studies (20 cohorts: 11 499 patients) were included in the meta-analyses. Abnormal HRT was a predictive marker for all the end points in heart failure patients and more markedly in postacute myocardial infarction patients, where 9 out of the 10 cohorts had an ejection fraction >30%. In postacute myocardial infarction patients, HRT had pooled risk ratios of 3.53 (95% confidence interval [CI], 2.54-4.90), 4.82 (95% CI, 3.12-7.45), and 4.48 (95% CI, 3.04-6.60), and positive likelihood ratios of 3.5 (95% CI, 2.6-4.8), 4.1 (95% CI, 3.0-5.7), and 2.7 (95% CI, 2.2-3.3) for total mortality, CD, and arrhythmic events, respectively. The combination of abnormal HRT and T-wave alternans (5 cohorts: 1516 patients) increased the predictive power for CD and arrhythmic events.

CONCLUSIONS

HRT is a powerful predictor of both CD and arrhythmic events, particularly in postacute myocardial infarction patients with ejection fraction >30%. HRT power increases in combination with T-wave alternans analysis.

Heart Failure: Diagnosis, Severity Estimation and Prediction of Adverse Events Through Machine Learning Techniques

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3-5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented.

Interactions between Activation and Repolarization Restitution Properties in the Intact Human Heart: In-Vivo Whole-Heart Data and Mathematical Description

BACKGROUND

The restitution of the action potential duration (APDR) and conduction velocity (CVR) are mechanisms whereby cardiac excitation and repolarization adapt to changes in heart rate. They modulate the vulnerability to dangerous arrhythmia, but the mechanistic link between restitution and arrhythmogenesis remains only partially understood.

METHODS

This paper provides an experimental and theoretical study of repolarization and excitation restitution properties and their interactions in the intact human epicardium. The interdependence between excitation and repolarization dynamic is studied in 8 patients (14 restitution protocols, 1722 restitution curves) undergoing global epicardial mapping with multi-electrode socks before open heart surgery. A mathematical description of the contribution of both repolarization and conduction dynamics to the steepness of the APDR slope is proposed.

RESULTS

This study demonstrates that the APDR slope is a function of both activation and repolarization dynamics. At short cycle length, conduction delay significantly increases the APDR slope by interacting with the diastolic interval. As predicted by the proposed mathematical formulation, the APDR slope was more sensitive to activation time prolongation than to the simultaneous shortening of repolarization time. A steep APDR slope was frequently identified, with 61% of all cardiac sites exhibiting an APDR slope > 1, suggesting that a slope > 1 may not necessarily promote electrical instability in the human epicardium. APDR slope did not change for different activation or repolarization times, and it was not a function of local baseline APD. However, it was affected by the spatial organization of electrical excitation, suggesting that in tissue APDR is not a unique function of local electrophysiological properties. Spatial heterogeneity in both activation and repolarization restitution contributed to the increase in the modulated dispersion of repolarization, which for short cycle length was as high as 250 ms. Heterogeneity in conduction velocity restitution can translate into both activation and repolarization dispersion and increase cardiac instability. The proposed mathematical formulation shows an excellent agreement with the experimental data (correlation coefficient r = 0.94) and provides a useful tool for the understanding of the complex interactions between activation and repolarization restitution properties as well as between their measurements.