Genetic Architecture of Acute Myocarditis and the Overlap With Inherited Cardiomyopathy.

BACKGROUND: Acute myocarditis is an inflammatory condition that may herald the onset of dilated cardiomyopathy (DCM) or arrhythmogenic cardiomyopathy (ACM). We investigated the frequency and clinical consequences of DCM and ACM genetic variants in a population-based cohort of patients with acute myocarditis. METHODS: This was a population-based cohort of 336 consecutive patients with acute myocarditis enrolled in London and Maastricht. All participants underwent targeted DNA sequencing for well-characterized cardiomyopathy-associated genes with comparison to healthy controls (n=1053) sequenced on the same platform. Case ascertainment in England was assessed against national hospital admission data. The primary outcome was all-cause mortality. RESULTS: Variants that would be considered pathogenic if found in a patient with DCM or ACM were identified in 8% of myocarditis cases compared with <1% of healthy controls (P=0.0097). In the London cohort (n=230; median age, 33 years; 84% men), patients were representative of national myocarditis admissions (median age, 32 years; 71% men; 66% case ascertainment), and there was enrichment of rare truncating variants (tv) in ACM-associated genes (3.1% of cases versus 0.4% of controls; odds ratio, 8.2; P=0.001). This was driven predominantly by DSP-tv in patients with normal LV ejection fraction and ventricular arrhythmia. In Maastricht (n=106; median age, 54 years; 61% men), there was enrichment of rare truncating variants in DCM-associated genes, particularly TTN-tv, found in 7% (all with left ventricular ejection fraction <50%) compared with 1% in controls (odds ratio, 3.6; P=0.0116). Across both cohorts over a median of 5.0 years (interquartile range, 3.9-7.8 years), all-cause mortality was 5.4%. Two-thirds of deaths were cardiovascular, attributable to worsening heart failure (92%) or sudden cardiac death (8%). The 5-year mortality risk was 3.3% in genotype-negative patients versus 11.1% for genotype-positive patients (Padjusted=0.08). CONCLUSIONS: We identified DCM- or ACM-associated genetic variants in 8% of patients with acute myocarditis. This was dominated by the identification of DSP-tv in those with normal left ventricular ejection fraction and TTN-tv in those with reduced left ventricular ejection fraction. Despite differences between cohorts, these variants have clinical implications for treatment, risk stratification, and family screening. Genetic counseling and testing should be considered in patients with acute myocarditis to help reassure the majority while improving the management of those with an underlying genetic variant.

Your Heart Function Has Normalized-What Next After TRED-HF?

PURPOSE OF REVIEW: With the widespread implementation of contemporary disease-modifying heart failure therapy, the rates of normalization of ejection fraction are continuously increasing. The TRED-HF trial confirmed that heart failure remission rather than complete recovery is typical in patients with dilated cardiomyopathy who respond to therapy. The present review outlines key points related to the management and knowledge gaps of this growing patient group, focusing on patients with non-ischaemic dilated cardiomyopathy. RECENT FINDINGS: There is substantial heterogeneity among patients with normalized ejection fraction. The specific etiology is likely to affect the outcome, although a multiple-hit phenotype is frequent and may not be identified without comprehensive characterization. A monogenic or polygenic genetic susceptibility is common. Ongoing pathophysiological processes may be unraveled with advanced cardiac imaging, biomarkers, multi-omics, and machine learning technologies. There are limited studies that have investigated the withdrawal of specific heart failure therapies in these patients. Diuretics may be safely withdrawn if there is no evidence of congestion, while continued therapy with at least some disease-modifying therapy is likely to be required to reduce myocardial workload and sustain remission for the vast majority. Understanding the underlying disease mechanisms of patients with normalized ejection fraction is crucial in identifying markers of myocardial relapse and guiding individualized therapy in the future. Ongoing clinical trials should inform personalized approaches to therapy.

Exposure to Elevated Nitrogen Dioxide Concentrations and Cardiac Remodeling in Patients With Dilated Cardiomyopathy.

BACKGROUND: Empirical evidence suggests a strong link between exposure to air pollution and heart failure incidence, hospitalizations, and mortality, but the biological basis of this remains unclear. We sought to determine the relationship between differential air pollution levels and changes in cardiac structure and function in patients with dilated cardiomyopathy. METHODS AND RESULTS: We undertook a prospective longitudinal observational cohort study of patients in England with dilated cardiomyopathy (enrollment 2009-2015, n = 716, 66% male, 85% Caucasian) and conducted cross sectional analysis at the time of study enrollment. Annual average air pollution exposure estimates for nitrogen dioxide (NO2) and particulate matter with diameter of 2.5 µm or less (PM2.5) at enrolment were assigned to each residential postcode (on average 12 households). The relationship between air pollution and cardiac morphology was assessed using linear regression modelling. Greater ambient exposure to NO2 was associated with higher indexed left ventricular (LV) mass (4.3 g/m2 increase per interquartile range increase in NO2, 95% confidence interval 1.9-7.0 g/m2) and lower LV ejection fraction (-1.5% decrease per interquartile range increase in NO2, 95% confidence interval -2.7% to -0.2%), independent of age, sex, socioeconomic status, and clinical covariates. The associations were robust to adjustment for smoking status and geographical clustering by postcode area. The effect of air pollution on LV mass was greatest in women. These effects were specific to NO2 exposure. CONCLUSIONS: Exposure to air pollution is associated with raised LV mass and lower LV ejection fraction, with the strongest effect in women. Although epidemiological associations between air pollution and heart failure have been established and supported by preclinical studies, our findings provide novel empirical evidence of cardiac remodeling and exposure to air pollution with important clinical and public health implications.

Left ventricular shape predicts arrhythmic risk in fibrotic dilated cardiomyopathy.

AIMS: Remodelling of the left ventricular (LV) shape is one of the hallmarks of non-ischaemic dilated cardiomyopathy (DCM) and may contribute to ventricular arrhythmias and sudden cardiac death. We sought to investigate a novel three dimensional (3D) shape analysis approach to quantify LV remodelling for arrhythmia prediction in DCM. METHODS AND RESULTS: We created 3D LV shape models from end-diastolic cardiac magnetic resonance images of 156 patients with DCM and late gadolinium enhancement (LGE). Using the shape models, principle component analysis, and Cox-Lasso regression, we derived a prognostic LV arrhythmic shape (LVAS) score which identified patients who reached a composite arrhythmic endpoint of sudden cardiac death, aborted sudden cardiac death, and sustained ventricular tachycardia. We also extracted geometrical metrics to look for potential prognostic markers. During a follow-up period of up to 16 years (median 7.7, interquartile range: 3.9), 25 patients met the arrhythmic endpoint. The optimally prognostic LV shape for predicting the time-to arrhythmic event was a paraboloidal longitudinal profile, with a relatively wide base. The corresponding LVAS was associated with arrhythmic events in univariate Cox regression (hazard ratio = 2.0 per quartile; 95% confidence interval: 1.3-2.9), in univariate Cox regression with propensity score adjustment, and in three multivariate models; with LV ejection fraction, New York Heart Association Class III/IV (Model 1), implantable cardioverter-defibrillator receipt (Model 2), and cardiac resynchronization therapy (Model 3). CONCLUSION: Biomarkers of LV shape remodelling in DCM can help to identify the patients at greatest risk of lethal ventricular arrhythmias.

Assessing left ventricular systolic function: from ejection fraction to strain analysis.

The measurement of left ventricular ejection fraction (LVEF) is a ubiquitous component of imaging studies used to evaluate patients with cardiac conditions and acts as an arbiter for many management decisions. This follows early trials investigating heart failure therapies which used a binary LVEF cut-off to select patients with the worst prognosis, who may gain the most benefit. Forty years on, the cardiac disease landscape has changed. Left ventricular ejection fraction is now a poor indicator of prognosis for many heart failure patients; specifically, for the half of patients with heart failure and truly preserved ejection fraction (HF-PEF). It is also recognized that LVEF may remain normal amongst patients with valvular heart disease who have significant myocardial dysfunction. This emphasizes the importance of the interaction between LVEF and left ventricular geometry. Guidelines based on LVEF may therefore miss a proportion of patients who would benefit from early intervention to prevent further myocardial decompensation and future adverse outcomes. The assessment of myocardial strain, or intrinsic deformation, holds promise to improve these issues. The measurement of global longitudinal strain (GLS) has consistently been shown to improve the risk stratification of patients with heart failure and identify patients with valvular heart disease who have myocardial decompensation despite preserved LVEF and an increased risk of adverse outcomes. To complete the integration of GLS into routine clinical practice, further studies are required to confirm that such approaches improve therapy selection and accordingly, the outcome for patients.

Cardiovascular Magnetic Resonance in Heritable Cardiomyopathies.

Cardiovascular magnetic resonance represents the imaging modality of choice for the investigation of patients with heritable cardiomyopathies. The combination of gold-standard volumetric analysis with tissue characterization can deliver precise phenotypic evaluation of both cardiac morphology and the underlying myocardial substrate. Cardiovascular magnetic resonance additionally has an established role in risk-stratifying patients with heritable cardiomyopathy and an emerging role in guiding therapies. This article explores the application and utility of cardiovascular magnetic resonance techniques with specific focus on the major heritable cardiomyopathies.

Withdrawal of pharmacological treatment for heart failure in patients with recovered dilated cardiomyopathy (TRED-HF): an open-label, pilot, randomised trial.

BACKGROUND: Patients with dilated cardiomyopathy whose symptoms and cardiac function have recovered often ask whether their medications can be stopped. The safety of withdrawing treatment in this situation is unknown. METHODS: We did an open-label, pilot, randomised trial to examine the effect of phased withdrawal of heart failure medications in patients with previous dilated cardiomyopathy who were now asymptomatic, whose left ventricular ejection fraction (LVEF) had improved from less than 40% to 50% or greater, whose left ventricular end-diastolic volume (LVEDV) had normalised, and who had an N-terminal pro-B-type natriuretic peptide (NT-pro-BNP) concentration less than 250 ng/L. Patients were recruited from a network of hospitals in the UK, assessed at one centre (Royal Brompton and Harefield NHS Foundation Trust, London, UK), and randomly assigned (1:1) to phased withdrawal or continuation of treatment. After 6 months, patients in the continued treatment group had treatment withdrawn by the same method. The primary endpoint was a relapse of dilated cardiomyopathy within 6 months, defined by a reduction in LVEF of more than 10% and to less than 50%, an increase in LVEDV by more than 10% and to higher than the normal range, a two-fold rise in NT-pro-BNP concentration and to more than 400 ng/L, or clinical evidence of heart failure, at which point treatments were re-established. The primary analysis was by intention to treat. This trial is registered with ClinicalTrials.gov, number NCT02859311. FINDINGS: Between April 21, 2016, and Aug 22, 2017, 51 patients were enrolled. 25 were randomly assigned to the treatment withdrawal group and 26 to continue treatment. Over the first 6 months, 11 (44%) patients randomly assigned to treatment withdrawal met the primary endpoint of relapse compared with none of those assigned to continue treatment (Kaplan-Meier estimate of event rate 45·7% [95% CI 28·5-67·2]; p=0·0001). After 6 months, 25 (96%) of 26 patients assigned initially to continue treatment attempted its withdrawal. During the following 6 months, nine patients met the primary endpoint of relapse (Kaplan-Meier estimate of event rate 36·0% [95% CI 20·6-57·8]). No deaths were reported in either group and three serious adverse events were reported in the treatment withdrawal group: hospital admissions for non-cardiac chest pain, sepsis, and an elective procedure. INTERPRETATION: Many patients deemed to have recovered from dilated cardiomyopathy will relapse following treatment withdrawal. Until robust predictors of relapse are defined, treatment should continue indefinitely. FUNDING: British Heart Foundation, Alexander Jansons Foundation, Royal Brompton Hospital and Imperial College London, Imperial College Biomedical Research Centre, Wellcome Trust, and Rosetrees Trust.

Scar shape analysis and simulated electrical instabilities in a non-ischemic dilated cardiomyopathy patient cohort.

This paper presents a morphological analysis of fibrotic scarring in non-ischemic dilated cardiomyopathy, and its relationship to electrical instabilities which underlie reentrant arrhythmias. Two dimensional electrophysiological simulation models were constructed from a set of 699 late gadolinium enhanced cardiac magnetic resonance images originating from 157 patients. Areas of late gadolinium enhancement (LGE) in each image were assigned one of 10 possible microstructures, which modelled the details of fibrotic scarring an order of magnitude below the MRI scan resolution. A simulated programmed electrical stimulation protocol tested each model for the possibility of generating either a transmural block or a transmural reentry. The outcomes of the simulations were compared against morphological LGE features extracted from the images. Models which blocked or reentered, grouped by microstructure, were significantly different from one another in myocardial-LGE interface length, number of components and entropy, but not in relative area and transmurality. With an unknown microstructure, transmurality alone was the best predictor of block, whereas a combination of interface length, transmurality and number of components was the best predictor of reentry in linear discriminant analysis.

Sudden Cardiac Death Prediction in Non-ischemic Dilated Cardiomyopathy: a Multiparametric and Dynamic Approach.

PURPOSE OF REVIEW: Sudden cardiac death is recognised as a devastating consequence of non-ischaemic dilated cardiomyopathy. Although implantable cardiac defibrillators offer protection against some forms of sudden death, the identification of patients in this population most likely to benefit from this therapy remains challenging and controversial. In this review, we evaluate current guidelines and explore established and novel predictors of sudden cardiac death in patients with non-ischaemic dilated cardiomyopathy. RECENT FINDINGS: Current international guidelines for primary prevention implantable defibrillator therapy do not result in improved longevity for many patients with non-ischemic cardiomyopathy and severe left ventricular dysfunction. More precise methods for identifying higher-risk patients that derive true prognostic benefit from this therapy are required. Dynamic and multi-parametric characterization of myocardial, electrical, serological and genetic substrate offers novel strategies for predicting major arrhythmic risk. Balancing the risk of non-sudden death offers an opportunity to personalize therapy and avoid unnecessary device implantation for those less likely to derive benefit.

Personalizing Risk Stratification for Sudden Death in Dilated Cardiomyopathy: The Past, Present, and Future.

Results from the DANISH Study (Danish Study to Assess the Efficacy of ICDs in Patients With Non-Ischemic Systolic Heat Failure on Mortality) suggest that for many patients with dilated cardiomyopathy (DCM), implantable cardioverter-defibrillators do not increase longevity. Accurate identification of patients who are more likely to die of an arrhythmia and less likely to die of other causes is required to ensure improvement in outcomes and wise use of resources. Until now, left ventricular ejection fraction has been used as a key criterion for selecting patients with DCM for an implantable cardioverter-defibrillator for primary prevention purposes. However, registry data suggest that many patients with DCM and an out-of-hospital cardiac arrest do not have a markedly reduced left ventricular ejection fraction. In addition, many patients with reduced left ventricular ejection fraction die of nonsudden causes of death. Methods to predict a higher or lower risk of sudden death include the detection of myocardial fibrosis (a substrate for ventricular arrhythmia), microvolt T-wave alternans (a marker of electrophysiological vulnerability), and genetic testing. Midwall fibrosis is identified by late gadolinium enhancement cardiovascular magnetic resonance imaging in ≈30% of patients and provides incremental value in addition to left ventricular ejection fraction for the prediction of sudden cardiac death events. Microvolt T-wave alternans represents another promising predictor, supported by large meta-analyses that have highlighted the negative predictive value of this test. However, neither of these strategies have been routinely adopted for risk stratification in clinical practice. More convincing data from randomized trials are required to inform the management of patients with these features. Understanding of the genetics of DCM and how specific mutations affect arrhythmic risk is also rapidly increasing. The finding of a mutation in lamin A/C, the cause of ≈6% of idiopathic DCM, commonly underpins more aggressive management because of the malignant nature of the associated phenotype. With the expansion of genetic sequencing, the identification of further high-risk mutations appears likely, leading to better-informed clinical decision making and providing insight into disease mechanisms. Over the next 5 to 10 years, we expect these techniques to be integrated into the existing algorithm to form a more sensitive, specific, and cost-effective approach to the selection of patients with DCM for implantable cardioverter-defibrillator implantation.

Association Between Midwall Late Gadolinium Enhancement and Sudden Cardiac Death in Patients With Dilated Cardiomyopathy and Mild and Moderate Left Ventricular Systolic Dysfunction.

BACKGROUND: Current guidelines only recommend the use of an implantable cardioverter defibrillator in patients with dilated cardiomyopathy for the primary prevention of sudden cardiac death (SCD) in those with a left ventricular ejection fraction (LVEF) <35%. However, registries of out-of-hospital cardiac arrests demonstrate that 70% to 80% of such patients have an LVEF >35%. Patients with an LVEF >35% also have low competing risks of death from nonsudden causes. Therefore, those at high risk of SCD may gain longevity from successful implantable cardioverter defibrillator therapy. We investigated whether late gadolinium enhancement (LGE) cardiovascular magnetic resonance identified patients with dilated cardiomyopathy without severe LV systolic dysfunction at high risk of SCD. METHODS: We prospectively investigated the association between midwall LGE and the prespecified primary composite outcome of SCD or aborted SCD among consecutive referrals with dilated cardiomyopathy and an LVEF ≥40% to our center between January 2000 and December 2011 who did not have a preexisting indication for implantable cardioverter defibrillator implantation. RESULTS: Of 399 patients (145 women, median age 50 years, median LVEF 50%, 25.3% with LGE) followed for a median of 4.6 years, 18 of 101 (17.8%) patients with LGE reached the prespecified end point, compared with 7 of 298 (2.3%) without (hazard ratio [HR], 9.2; 95% confidence interval [CI], 3.9-21.8; P<0.0001). Nine patients (8.9%) with LGE compared with 6 (2.0%) without (HR, 4.9; 95% CI, 1.8-13.5; P=0.002) died suddenly, whereas 10 patients (9.9%) with LGE compared with 1 patient (0.3%) without (HR, 34.8; 95% CI, 4.6-266.6; P<0.001) had aborted SCD. After adjustment, LGE predicted the composite end point (HR, 9.3; 95% CI, 3.9-22.3; P<0.0001), SCD (HR, 4.8; 95% CI, 1.7-13.8; P=0.003), and aborted SCD (HR, 35.9; 95% CI, 4.8-271.4; P<0.001). Estimated HRs for the primary end point for patients with an LGE extent of 0% to 2.5%, 2.5% to 5%, and >5% compared with those without LGE were 10.6 (95% CI, 3.9-29.4), 4.9 (95% CI, 1.3-18.9), and 11.8 (95% CI, 4.3-32.3), respectively. CONCLUSIONS: Midwall LGE identifies a group of patients with dilated cardiomyopathy and an LVEF ≥40% at increased risk of SCD and low risk of nonsudden death who may benefit from implantable cardioverter defibrillator implantation. CLINICAL TRIAL REGISTRATION: URL: http://clinicaltrials.gov. Unique identifier: NCT00930735.

Comparative prognostic importance of measures of left atrial structure and function in non-ischaemic dilated cardiomyopathy.

AIMS: To compare the association between measures of left atrial (LA) structure and function, derived from cardiovascular magnetic resonance (CMR), with cardiovascular (CV) death or non-fatal heart failure (HF) events in patients with non-ischaemic dilated cardiomyopathy (DCM). METHODS AND RESULTS: CMR studies of 580 prospectively recruited patients with DCM in sinus rhythm (median age 54 [interquartile range 44-64] years, 61% men, median LVEF 42% [30-51%]) were analysed for measures of LA structure (left atrial maximum volume index [LAVImax], left atrial minimum volume index [LAVImin]) and function (left atrial emptying fraction [LAEF], left atrial reservoir strain [LARS], left atrial conduit strain [LACS] and left atrial booster strain [LABS]). Over median follow-up of 7.4 years, 103 patients (18%) met the primary endpoint. Apart from LACS, each measure of LA structure and function was associated with the primary endpoint after adjusting for other important prognostic variables. The addition of each LA metric to a baseline model containing the same important prognostic covariates improved model discrimination, with LAVImin providing the greatest improvement (C-statistic improvement: 0.702 to 0.738; χ2 test comparing likelihood ratio p < 0.0001; categorical net reclassification index: 0.210 (95% CI 0.023-0.392)). Patients in the highest tercile of LAVImin had similar event rates to those with persistent atrial fibrillation. Measures of LA strain did not enhance model discrimination above LA volumetric measures. CONCLUSION: Measure of left atrial structure and function offer important prognostic information in patients with DCM and enhance prediction of adverse outcomes. LA strain was not incremental to volumetric analysis for risk prediction.

Assessing the association between genetic and phenotypic features of dilated cardiomyopathy and outcome in patients with coronary artery disease.

AIMS: To examine the relevance of genetic and cardiovascular magnetic resonance (CMR) features of dilated cardiomyopathy (DCM) in individuals with coronary artery disease (CAD). METHODS AND RESULTS: This study includes two cohorts. First, individuals with CAD recruited into the UK Biobank (UKB) were evaluated. Second, patients with CAD referred to a tertiary centre for evaluation with late gadolinium enhancement (LGE)-CMR were recruited (London cohort); patients underwent genetic sequencing as part of the research protocol and long-term follow-up. From 31 154 individuals with CAD recruited to UKB, rare pathogenic variants in DCM genes were associated with increased risk of death or major adverse cardiac events (hazard ratio 1.57, 95% confidence interval [CI] 1.22-2.01, p < 0.001). Of 1619 individuals with CAD included from the UKB CMR substudy, participants with a rare variant in a DCM-associated gene had lower left ventricular ejection fraction (LVEF) compared to genotype negative individuals (mean 47 ± 10% vs. 57 ± 8%, p < 0.001). Of 453 patients in the London cohort, 63 (14%) had non-infarct pattern LGE (NI-LGE) on CMR. Patients with NI-LGE had lower LVEF (mean 38 ± 18% vs. 48 ± 16%, p < 0.001) compared to patients without NI-LGE, with no significant difference in the burden of rare protein altering variants in DCM-associated genes between groups (9.5% vs. 6.7%, odds ratio 1.5, 95% CI 0.4-4.3, p = 0.4). NI-LGE was not independently associated with adverse clinical outcomes. CONCLUSION: Rare pathogenic variants in DCM-associated genes impact left ventricular remodelling and outcomes in stable CAD. NI-LGE is associated with adverse remodelling but is not an independent predictor of outcome and had no rare genetic basis in our study.

Sex Differences in the Clinical Presentation and Natural History of Dilated Cardiomyopathy.

BACKGROUND: Biological sex has a diverse impact on the cardiovascular system. Its influence on dilated cardiomyopathy (DCM) remains unresolved. OBJECTIVES: This study aims to investigate sex-specific differences in DCM presentation, natural history, and prognostic factors. METHODS: The authors conducted a prospective observational cohort study of DCM patients assessing baseline characteristics, cardiac magnetic resonance imaging, biomarkers, and genotype. The composite outcome was cardiovascular mortality or major heart failure (HF) events. RESULTS: Overall, 206 females and 398 males with DCM were followed for a median of 3.9 years. At baseline, female patients had higher left ventricular ejection fraction, smaller left ventricular volumes, less prevalent mid-wall myocardial fibrosis (23% vs 42%), and lower high-sensitivity cardiac troponin I than males (all P < 0.05) with no difference in time from diagnosis, age at enrollment, N-terminal pro-B-type natriuretic peptide levels, pathogenic DCM genetic variants, myocardial fibrosis extent, or medications used for HF. Despite a more favorable profile, the risk of the primary outcome at 2 years was higher in females than males (8.6% vs 4.4%, adjusted HR: 3.14; 95% CI: 1.55-6.35; P = 0.001). Between 2 and 5 years, the effect of sex as a prognostic modifier attenuated. Age, mid-wall myocardial fibrosis, left ventricular ejection fraction, left atrial volume, N-terminal pro-B-type natriuretic peptide, high-sensitivity cardiac troponin I, left bundle branch block, and NYHA functional class were not sex-specific prognostic factors. CONCLUSIONS: The authors identified a novel paradox in prognosis for females with DCM. Female DCM patients have a paradoxical early increase in major HF events despite less prevalent myocardial fibrosis and a milder phenotype at presentation. Future studies should interrogate the mechanistic basis for these sex differences.

Precision therapy in dilated cardiomyopathy: Pipedream or paradigm shift?

Precision medicine for cardiomyopathies holds great promise to improve patient outcomes costs by shifting the focus to patient-specific treatment decisions, maximising the use of therapies most likely to lead to benefit and minimising unnecessary intervention. Dilated cardiomyopathy (DCM), characterised by left ventricular dilatation and impairment, is a major cause of heart failure globally. Advances in genomic medicine have increased our understanding of the genetic architecture of DCM. Understanding the functional implications of genetic variation to reveal genotype-specific disease mechanisms is the subject of intense investigation, with advanced cardiac imaging and mutliomics approaches playing important roles. This may lead to increasing use of novel, targeted therapy. Individualised treatment and risk stratification is however made more complex by the modifying effects of common genetic variation and acquired environmental factors that help explain the variable expressivity of rare genetic variants and gene elusive disease. The next frontier must be expanding work into early disease to understand the mechanisms that drive disease expression, so that the focus can be placed on disease prevention rather than management of later symptomatic disease. Overcoming these challenges holds the key to enabling a paradigm shift in care from the management of symptomatic heart failure to prevention of disease.

Machine learning analysis of complex late gadolinium enhancement patterns to improve risk prediction of major arrhythmic events.

Background: Machine learning analysis of complex myocardial scar patterns affords the potential to enhance risk prediction of life-threatening arrhythmia in stable coronary artery disease (CAD). Objective: To assess the utility of computational image analysis, alongside a machine learning (ML) approach, to identify scar microstructure features on late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) that predict major arrhythmic events in patients with CAD. Methods: Patients with stable CAD were prospectively recruited into a CMR registry. Shape-based scar microstructure features characterizing heterogeneous ('peri-infarct') and homogeneous ('core') fibrosis were extracted. An ensemble of machine learning approaches were used for risk stratification, in addition to conventional analysis using Cox modeling. Results: Of 397 patients (mean LVEF 45.4 ± 16.0) followed for a median of 6 years, 55 patients (14%) experienced a major arrhythmic event. When applied within an ML model for binary classification, peri-infarct zone (PIZ) entropy, peri-infarct components and core interface area outperformed a model representative of the current standard of care (LVEF<35% and NYHA>Class I): AUROC (95%CI) 0.81 (0.81-0.82) vs. 0.64 (0.63-0.65), p = 0.002. In multivariate cox regression analysis, these features again remained significant after adjusting for LVEF<35% and NYHA>Class I: PIZ entropy hazard ratio (HR) 1.88, 95% confidence interval (CI) 1.38-2.56, p < 0.001; number of PIZ components HR 1.34, 95% CI 1.08-1.67, p = 0.009; core interface area HR 1.6, 95% CI 1.29-1.99, p = <0.001. Conclusion: Machine learning models using LGE-CMR scar microstructure improved arrhythmic risk stratification as compared to guideline-based clinical parameters; highlighting a potential novel approach to identifying candidates for implantable cardioverter defibrillators in stable CAD.