Deep neural network-based clustering of deformation curves reveals novel disease features in PLN pathogenic variant carriers

Echocardiographic deformation curves provide detailed information on myocardial function. Deep neural networks (DNNs) may enable automated detection of disease features in deformation curves, and improve the clinical assessment of these curves. We aimed to investigate whether an explainable DNN-based pipeline can be used to detect and visualize disease features in echocardiographic deformation curves of phospholamban (PLN) p.Arg14del variant carriers. A DNN was trained to discriminate PLN variant carriers (n = 278) from control subjects (n = 621) using raw deformation curves obtained by 2D-speckle tracking in the longitudinal axis. A visualization technique was used to identify the parts of these curves that were used by the DNN for classification. The PLN variant carriers were clustered according to the output of the visualization technique. The DNN showed excellent discriminatory performance (C-statistic 0.93 [95% CI 0.87-0.97]). We identified four clusters with PLN-associated disease features in the deformation curves. Two clusters showed previously described features: apical post-systolic shortening and reduced systolic strain. The two other clusters revealed novel features, both reflecting delayed relaxation. Additionally, a fifth cluster was identified containing variant carriers without disease features in the deformation curves, who were classified as controls by the DNN. This latter cluster had a very benign disease course regarding development of ventricular arrhythmias. Applying an explainable DNN-based pipeline to myocardial deformation curves enables automated detection and visualization of disease features. In PLN variant carriers, we discovered novel disease features which may improve individual risk stratification. Applying this approach to other diseases will further expand our knowledge on disease-specific deformation patterns. Overview of the deep neural network-based pipeline for feature detection in myocardial deformation curves. Firstly, phospholamban (PLN) p.Arg14del variant carriers and controls were selected and a deep neural network (DNN) was trained to detect the PLN variant carriers. Subsequently, a clustering-based approach was performed on the attention maps of the DNN, which revealed 4 distinct phenotypes of PLN variant carriers with different prognoses. Moreover, a cluster without features and a benign prognosis was detected.

Left atrial remodeling in mitral regurgitation: A combined experimental-computational study

Aims

Progressive changes to left atrial (LA) structure and function following mitral regurgitation (MR) remain incompletely understood. This study aimed to demonstrate potential underlying mechanisms using experimental canine models and computer simulations.

Methods

A canine model of MR was created by cauterization of mitral chordae followed by radiofrequency ablation-induced left bundle-branch block (LBBB) after 4 weeks (MR-LBBB group). Animals with LBBB alone served as control. Echocardiography was performed at baseline, acutely after MR induction, and at 4 and 20 weeks, and correlated with histology and computer simulations.

Results

Acute MR augmented LA reservoir and contractile strain (40±4 to 53±6% and -11±5 to -22±9% respectively, p<0.05). LA fractional area change increased significantly (47±4 to 56±4%, p<0.05) while LA end-systolic area remained unchanged (7.2±1.1 versus 7.9±1.1 cm2 respectively, p = 0.08). LA strain ‘pseudonormalized’ after 4 weeks and decompensated at 20 weeks with both strains decreasing to 25±6% and -3±2% respectively (p<0.05) together with a progressive increase in LA end-systolic area (7.2±1.1 to 14.0±6.3 cm2, p<0.05). In the LBBB-group, LA remodeling was less pronounced. Histology showed a trend towards increased interstitial fibrosis in the LA of the MR-LBBB group. Computer simulations indicated that the progressive changes in LA structure and function are a combination of progressive eccentric remodeling and fibrosis.

Conclusion

MR augmented LA strain acutely to supranormal values without significant LA dilation. However, over time, LA strain gradually decreases (pseudornormal and decompensated) with LA dilation. Histology and computer simulations indicated a correlation to a varying degree of LA eccentric remodeling and fibrosis.

Feasibility, safety and outcomes of upgrading to left bundle branch pacing in patients with right ventricular pacing induced cardiomyopathy

Funding Acknowledgements

Type of funding sources: None.

Background

Right ventricular pacing (RVP) induces abnormal electrical activation and asynchronous ventricular contraction and leads to pacing induced cardiomyopathy (PICM) in 10-20% of patients. Cardiac resynchronization therapy (CRT) utilizing biventricular pacing (BVP) is the recommended treatment. Left bundle branch pacing (LBBP) is a novel physiological pacing technique which may serve as an alternative to CRT. This study assessed feasibility and outcomes of LBBP delivered CRT in patients with PICM.

Methods

Twenty consecutive patients with PICM who received an upgrade of their pacemaker to LBBP were prospectively studied. Acute success rate, complications, functional and echocardiographic response and hospitalization for heart failure within six months from implantation were evaluated.

Results

LBBP was successfully delivered in all patients. Median duration of RVP before upgrade to LBBP was 3.8 years and the RVP percentage was 99. LBBP resulted in significant QRS narrowing (from 192 ± 18 to 131 ± 17 ms (p&lt;0.001)), improvement in LVEF (from 31 ± 6 percent to 44 ± 8 percent (p&lt;0.001)) and NYHA class (from 2.7 ± 0.5 to 1.4 ± 0.5 (p&lt;0.001)) at 6 months. No LBBP-related complications occurred and no hospitalization for heart failure or death occurred.

Conclusion

LBBP is feasible and safe in delivering CRT in PICM. Preliminary analyses demonstrated significant electrical resynchronization and favourable improvement in LV function and NYHA functional class at short term follow-up. Data need to be validated in large randomized controlled trials.

Feasibility, safety and outcomes of upgrading to left bundle branch pacing in patients with right ventricular pacing induced cardiomyopathy

BACKGROUND

Right ventricular pacing (RVP) induces abnormal electrical activation and asynchronous ventricular contraction and leads to pacing induced cardiomyopathy (PICM) in 10-20% of patients. Cardiac resynchronization therapy (CRT) utilizing biventricular pacing (BVP) is the recommended treatment. Left bundle branch pacing (LBBP) is a novel physiological pacing technique which may serve as an alternative to CRT. This study assessed feasibility and outcomes of LBBP delivered CRT in patients with PICM.

METHODS

Twenty consecutive patients with PICM who received an upgrade of their pacemaker to LBBP were prospectively studied. Acute success rate, complications, functional and echocardiographic response and hospitalization for heart failure within six months from implantation were evaluated.

RESULTS

LBBP was successfully delivered in all patients. Median duration of RVP before upgrade to LBBP was 3.8 years and the RVP percentage was 99. LBBP resulted in significant QRS narrowing (from 193 ± 18 to 130 ± 17 ms (p<0.001)), improvement in LVEF (from 32 ± 6 percent to 47 ± 8 percent (p<0.001)) and NYHA class (from 2.8 ± 0.4 to 1.4 ± 0.5 (p<0.001)) at 6 months. No LBBP-related complications occurred. No patients were hospitalized for heart failure or died.

CONCLUSION

LBBP is feasible and safe in delivering CRT in PICM. Preliminary analyses demonstrated significant electrical resynchronization and favourable improvement in LV function and NYHA functional class at short term follow-up. Data need to be validated in large randomized controlled trials. This article is protected by copyright. All rights reserved.

Hypothermia for Cardioprotection in Patients with St-Elevation Myocardial Infarction: Do Not Give It the Cold Shoulder Yet!

The timely revascularization of an occluded coronary artery is the cornerstone of treatment in patients with ST-elevation myocardial infarction (STEMI). As essential as this treatment is, it can also cause additional damage to cardiomyocytes that were still viable before reperfusion, increasing infarct size. This has been termed “myocardial reperfusion injury”. To date, there is still no effective treatment for myocardial reperfusion injury in patients with STEMI. While numerous attempts have been made to overcome this hurdle with various experimental therapies, the common denominator of these therapies is that, although they often work in the preclinical setting, they fail to demonstrate the same results in human trials. Hypothermia is an example of such a therapy. Although promising results were derived from experimental studies, multiple randomized controlled trials failed to do the same. This review includes a discussion of hypothermia as a potential treatment for myocardial reperfusion injury, including lessons learned from previous (negative) trials, advanced techniques and materials in current hypothermic treatment, and the possible future of hypothermia for cardioprotection in patients with STEMI.

Development of an algorithm for automatic classification of right ventricle deformation patterns in arrhythmogenic right ventricular cardiomyopathy

BACKGROUND

Different disease stages of arrhythmogenic right ventricular cardiomyopathy (ARVC) can be identified by right ventricle (RV) longitudinal deformation (strain) patterns. This requires assessment of the onset of shortening, (systolic) peak strain, and postsystolic index, which is time-consuming and prone to inter- and intra-observer variability. The aim of this study was to design and validate an algorithm to automatically classify RV deformation patterns.

METHODS

We developed an algorithm based on specific local characteristics from the strain curves to detect the parameters required for classification. Determination of the onset of shortening by the algorithm was compared to manual determination by an experienced operator in a dataset containing 186 RV strain curves from 26 subjects carrying a pathogenic plakophilin-2 (PKP2) mutation and 36 healthy subjects. Classification agreement between operator and algorithm was solely based on differences in onset shortening, as the remaining parameters required for classification of RV deformation patterns could be directly obtained from the strain curves.

RESULTS

The median difference between the onset of shortening determined by the experienced operator and by the automatic detector was 5.3 ms [inter-quartile range (IQR) 2.7-8.6 ms]. 96% of the differences were within 1 time frame. Both methods correlated significantly with ρ = 0.97 (P < .001). For 26 PKP2 mutation carriers, there was 100% agreement in classification between the algorithm and experienced operator.

CONCLUSION

The determination of the onset of shortening by the experienced operator was comparable to the algorithm. Our computer algorithm seems a promising method for the automatic classification of RV deformation patterns. The algorithm is publicly available at the MathWorks File Exchange.

Evaluation of Structural Progression in Arrhythmogenic Right Ventricular Dysplasia/Cardiomyopathy

Importance

Considerable research has described the arrhythmic course of arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C). However, objective data characterizing structural progression, such as ventricular enlargement and cardiac dysfunction, in ARVD/C are relatively scarce.

Objectives

To define the extent of structural progression, identify determinants of structural progression, and determine the association between structural progression and electrocardiographic (ECG) changes in patients with ARVD/C.

Design, Setting, and Participants

In this cohort study, first- and last-available echocardiograms of 85 patients with ARVD/C fulfilling 2010 Task Force diagnostic criteria (TFC) from a transatlantic ARVD/C registry were retrospectively compared to assess structural disease progression. Right ventricular (RV) size and systolic function between baseline and last follow-up were compared. The RV size was determined by RV outflow tract dimension, and RV and left ventricular (LV) systolic function were determined by RV fractional area change (RV-FAC) and LV ejection fraction (LVEF), respectively. Multivariable logistic regression was used to study associations between baseline characteristics and the occurrence of structural progression.

Main Outcomes and Measures

The main outcome was the change in variables indicating structural progression. Secondary outcomes were the correlation with electrical progression and identification of the association between baseline characteristics and occurence structural progression.

Results

Among the 85 patients with ARVD/C, mean (SD) age at baseline was 42.8 (14.4) years and 47 (55%) were men. After a mean (SD) follow-up of 6.4 (2.5) years, RV outflow tract dimension increased from 35 mm (interquartile range [IQR], 31 to 39) to 37 mm (IQR, 33 to 41) (P < .001), RV-FAC decreased from 39% (IQR, 33% to 44%) to 34% (IQR, 24% to 42%) (P < .001) (rate -3.3% per 5 years; IQR, -8.9% to 1.2%), indicating large interpatient variability. The LVEF decreased from 55% (IQR, 52% to 60%) to 54% (IQR, 49% to 57%) (P = .001) (rate, -0.2% per 5 years; IQR, -6.5% to 1.7%). Forty examinations were reanalyzed to establish the measurement error. Patients exceeding the measurement error by ±2 SDs were identified with significant progressive disease for RV, with a decrease in RV-FAC greater than 10% (n = 21) and, for LV, a decrease in LVEF greater than 7% (n = 23). Progression of RV disease was associated with depolarization criteria at baseline (odds ratio [OR], 9.0; 95% CI, 1.1-74.2; P = .04), whereas progression of LV disease was associated with phospholamban (PLN) mutation (OR, 8.8; 95% CI, 2.1-37.2; P = .003). There was no association between progressive RV/LV structural disease and newly developed ECG TFC.

Conclusions and Relevance

Structural dysfunction in ARVD/C is progressive with substantial interpatient variability. Significant structural RV progression was associated with prior depolarization abnormalities, whereas LV progression is modified by genetic background. Structural progression was not associated with development of new ECG TFC. The results of this study pave the way for designing and launching trials aimed at reducing structural progression in patients with ARVD/C.

The Prognostic Value of Right Ventricular Deformation Imaging in Early Arrhythmogenic Right Ventricular Cardiomyopathy

OBJECTIVES

The aim of this study was to investigate the prognostic value of echocardiographic deformation imaging in arrhythmogenic right ventricular cardiomyopathy (ARVC) to optimize family screening protocols.

BACKGROUND

ARVC is characterized by variable disease expressivity among family members, which complicates family screening protocols. Previous reports have shown that echocardiographic deformation imaging detects abnormal right ventricular (RV) deformation in the absence of established disease expression in ARVC.

METHODS

First-degree relatives of patients with ARVC were evaluated according to 2010 task force criteria, including RV deformation imaging (n = 128). Relatives fulfilling structural task force criteria were excluded for further analysis. At baseline, deformation patterns of the subtricuspid region were scored as type I (normal deformation), type II (delayed onset, decreased systolic peak, and post-systolic shortening), or type III (systolic stretching and large post-systolic shortening). The final study population comprised relatives who underwent a second evaluation during follow-up. Disease progression was defined as the development of a new 2010 task force criterion during follow-up that was absent at baseline.

RESULTS

Sixty-five relatives underwent a second evaluation after a mean follow-up period of 3.7 ± 2.1 years. At baseline, 28 relatives (43%) had normal deformation (type I), and 37 relatives (57%) had abnormal deformation (type II or III) in the subtricuspid region. Disease progression occurred in 4% of the relatives with normal deformation at baseline and in 43% of the relatives with abnormal deformation at baseline (p < 0.001). Positive and negative predictive values of abnormal deformation were, respectively, 43% (95% confidence interval: 27% to 61%) and 96% (95% confidence interval: 82% to 100%).

CONCLUSIONS

Normal RV deformation in the subtricuspid region is associated with absence of disease progression during nearly 4-year follow-up in relatives of patients with ARVC. Abnormal RV deformation seems to precede the established signs of ARVC. RV deformation imaging may potentially play an important role in ARVC family screening protocols.

Clinical characterisation and risk stratification of patients with arrhythmogenic right ventricular dysplasia/cardiomyopathy ≥50 years of age

Purpose

With the increased use of genetic testing for arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C), this disease is being increasingly recognised among elderly patients. However, elderly ARVD/C patients were underrepresented in prior cohorts. We aimed to describe the phenotypical characteristics and outcomes among ARVD/C patients surviving ≥50 years.

Methods

We assessed detailed phenotypical data of 29 patients who (1) presented at ≥50 years of age; and (2) fulfilled 2010 Task Force Criteria (TFC) for ARVD/C by last follow-up. Primary outcome was the occurrence of a major ventricular arrhythmia (sudden cardiac death, resuscitated sudden cardiac arrest or sustained ventricular tachycardia).

Results

The majority (55 %) of elderly ARVD/C subjects were male, with a mean age of 59.0 ± 5.8 years at presentation. Study participants fulfilled a median of six (IQR 5–8) TFC criteria by last follow-up, of which arrhythmia criteria were most frequent (97 %), followed by structural criteria (83 %), depolarisation criteria (72 %) and repolarisation criteria (69 %). By last follow-up, 15 (52 %) patients had experienced major ventricular arrhythmias. Most patients (n = 12) presented with this arrhythmia, while three experienced the event during 5.4 ± 3.2 years of follow-up. Compared with patients without an arrhythmic event, patients with major arrhythmias were more likely to be proband (p < 0.001) and male (p = 0.042). Likewise, survival free from sustained ventricular arrhythmia was lower among probands and males.

Conclusion

Phenotypic characteristics of elderly ARVD/C patients are characterised by depolarisation abnormalities and structural cardiac changes. Ventricular arrhythmias in this elderly cohort are associated with male gender and proband status.

Echo response and clinical outcome in CRT patients

Background

Change in left ventricular end-systolic volume (∆LVESV) is the most frequently used surrogate marker in measuring response to cardiac resynchronisation therapy (CRT). We investigated whether ∆LVESV is the best measure to discriminate between a favourable and unfavourable outcome and whether this is equally applicable to non-ischaemic and ischaemic cardiomyopathy.

Methods

205 CRT patients (age 65 ± 12 years, 69 % men) were included. At baseline and 6 months echocardiographic studies, exercise testing and laboratory measurements were performed. CRT response was assessed by: ∆LVESV, ∆LV ejection fraction (LVEF), ∆ interventricular mechanical delay, ∆VO₂ peak, ∆VE/VCO₂, ∆BNP, ∆creatinine, ∆NYHA, and ∆QRS. These were correlated to the occurrence of major adverse cardiac events (MACE) between 6 and 24 months.

Results

MACE occurred in 19 % of the patients (non-ischaemic: 13 %, ischaemic: 24 %). ∆LVESV remained the only surrogate marker for CRT response for the total population and patients with non-ischaemic cardiomyopathy, showing areas under the curve (AUC) of 0.69 and 0.850, respectively. For ischaemic cardiomyopathy, ∆BNP was the best surrogate marker showing an AUC of 0.66.

Conclusion

∆LVESV is an excellent surrogate marker measuring CRT response concerning long-term outcome for non-ischaemic cardiomyopathy. ∆LVESV is not suitable for ischaemic cardiomyopathy in which measuring CRT response remains difficult.

Arrhythmogenic Right Ventricular Dysplasia/Cardiomyopathy in the Pediatric Population: Clinical Characterization and Comparison With Adult-Onset Disease

OBJECTIVES

The aims of this study were to determine the clinical characteristics and outcomes of pediatric-onset arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C) and to compare these with those of adult-onset ARVD/C.

BACKGROUND

Improved early detection and increased awareness of ARVD/C have led to a growing group of pediatric patients seeking management recommendations. Prior studies have mainly included adults with ARVD/C; however, clinical features and outcomes may differ in pediatric subjects.

METHODS

Among 502 subjects fulfilling task force criteria for ARVD/C, we identified 75 (15%) with pediatric-onset disease (diagnosis at <18 years of age or probands presenting symptomatically at <18 years of age). Clinical characteristics and outcomes (sustained ventricular tachycardia, cardiac transplantation, and death) were compared between pediatric and adult patients.

RESULTS

Pediatric patients presented at 15.3 ± 2.4 years of age. Most pediatric patients were male (55%) and ARVD/C-associated mutation carriers (80%). One-fourth of pediatric patients presented with sudden cardiac death (15%) or resuscitated sudden cardiac arrest (11%). Compared with adults, pediatric patients were disproportionately mutation carriers (p = 0.002) but not more often male (p = 0.696) or probands (p = 0.371). Pediatric patients were more likely to present with sudden cardiac death (p = 0.003), whereas adults more often presented with sustained ventricular tachycardia (p = 0.017). There were no other phenotypic differences between the groups. During 8.4 ± 7.5 years of follow-up, survival free from sustained ventricular tachycardia (p = 0.359), cardiac transplantation (p = 0.523), and death (p = 0.359) was similar between pediatric and adult patients.

CONCLUSIONS

Pediatric patients with ARVD/C are typically male mutation carriers presenting in adolescence. Pediatric patients disproportionately present with sudden cardiac death. However, once diagnosed, clinical characteristics and outcomes are similar between pediatric and adult patients.

Volumetric Response beyond Six Months of Cardiac Resynchronization Therapy and Clinical Outcome

Aims

Response to cardiac resynchronization therapy (CRT) is often assessed six months after implantation. Our objective was to assess the number of patients changing from responder to non-responder between six and 14 months, so-called late non-responders, and compare them to patients who were responder both at six and 14 months, so-called stable responders. Furthermore, we assessed predictive values of six and 14-month response concerning clinical outcome.

Methods

105 patients eligible for CRT were enrolled. Clinical, laboratory, ECG, and echocardiographic parameters and patient-reported health status (Kansas City Cardiomyopathy Questionnaire [KCCQ]) were assessed before, and six and 14 months after implantation. Response was defined as ≥15% LVESV decrease as compared to baseline. Major adverse cardiac events (MACE) were registered until 24 months after implantation. Predictive values of six and 14-month response for MACE were examined.

Results

In total, 75 (71%) patients were six-month responders of which 12 (16%) patients became late non-responder. At baseline, late non-responders more often had ischemic cardiomyopathy and atrial fibrillation, higher BNP and less dyssynchrony compared to stable responders. At six months, late non-responders showed significantly less LVESV decrease, and higher creatinine levels. Mean KCCQ scores of late non-responders were lower than those of stable responders at every time point, with the difference being significant at 14 months. The 14 months response was a better predictor of MACE than six months response.

Conclusions

The assessment of treatment outcomes after six months of CRT could be premature and response rates beyond might better correlate to long-term clinical outcome.

Chest pain in the emergency room: a multicenter validation of the HEART Score

OBJECTIVE

Decision-making in chest pain patients is hampered by poor diagnostic power of patient's history, electrocardiogram, age, risk factors, and troponin. Each of these findings may be qualified with 0, 1, or 2 points. Together they compose the HEART score. We tested the hypothesis that the HEART score predicts major adverse cardiac events.

DESIGN

Retrospective multicenter analysis in patients presenting at the cardiology emergency room.

SETTING

Patient inclusion between January 1 and March 31, 2006.

PATIENTS

A total of 2161 patients were admitted, of which 910 patients (42%) presented with chest pain. Analysis was performed in 880 cases (96.7%).

MAIN OUTCOME MEASURES

The primary endpoint was a composite of acute myocardial infarction, percutaneous coronary intervention, coronary artery bypass graft surgery and death, within 6 weeks after presentation, together called major adverse cardiac events.

RESULTS

A total of 158 patients (17.95%) reached the primary endpoint. Ninety-two patients had an acute myocardial infarction (10.45%), 82 a percutaneous coronary intervention (9.32%), 36 a coronary artery bypass graft (4.09%), and 13 died (1.48%). Of 303 patients with HEART score 0 to 3, three (0.99%) had an endpoint. In 413 patients with HEART score 4 to 6, 48 cases (11.6%) reached an endpoint. In case of a HEART score of 7 to 10, an endpoint was reached in 107/164 cases (65.2%).

CONCLUSIONS

The HEART score helps in making accurate diagnostic and therapeutic decisions without the use of radiation or invasive procedures. The HEART score is an easy, quick, and reliable predictor of outcome in chest pain patients and can be used for triage.