ECG-only explainable deep learning algorithm predicts the risk for malignant ventricular arrhythmia in phospholamban cardiomyopathy.

BACKGROUND: Phospholamban (PLN) p.(Arg14del) variant carriers are at risk for development of malignant ventricular arrhythmia (MVA). Accurate risk stratification allows timely implantation of intracardiac defibrillators and is currently performed with a multimodality prediction model. OBJECTIVE: This study aimed to investigate whether an explainable deep learning-based approach allows risk prediction with only electrocardiogram (ECG) data. METHODS: A total of 679 PLN p.(Arg14del) carriers without MVA at baseline were identified. A deep learning-based variational auto-encoder, trained on 1.1 million ECGs, was used to convert the 12-lead baseline ECG into its FactorECG, a compressed version of the ECG that summarizes it into 32 explainable factors. Prediction models were developed by Cox regression. RESULTS: The deep learning-based ECG-only approach was able to predict MVA with a C statistic of 0.79 (95% CI, 0.76-0.83), comparable to the current prediction model (C statistic, 0.83 [95% CI, 0.79-0.88]; P = .054) and outperforming a model based on conventional ECG parameters (low-voltage ECG and negative T waves; C statistic, 0.65 [95% CI, 0.58-0.73]; P < .001). Clinical simulations showed that a 2-step approach, with ECG-only screening followed by a full workup, resulted in 60% less additional diagnostics while outperforming the multimodal prediction model in all patients. A visualization tool was created to provide interactive visualizations (https://pln.ecgx.ai). CONCLUSION: Our deep learning-based algorithm based on ECG data only accurately predicts the occurrence of MVA in PLN p.(Arg14del) carriers, enabling more efficient stratification of patients who need additional diagnostic testing and follow-up.

A Kinase Interacting Protein 1 regulates mitochondrial protein levels in energy metabolism and promotes mitochondrial turnover after exercise.

A Kinase Interacting Protein 1 (AKIP1) is a signalling adaptor that promotes mitochondrial respiration and attenuates mitochondrial oxidative stress in cultured cardiomyocytes. We sought to determine whether AKIP1 influences mitochondrial function and the mitochondrial adaptation in response to exercise in vivo. We assessed mitochondrial respiratory capacity, as well as electron microscopy and mitochondrial targeted-proteomics in hearts from mice with cardiomyocyte-specific overexpression of AKIP1 (AKIP1-TG) and their wild type (WT) littermates. These parameters were also assessed after four weeks of voluntary wheel running. In contrast to our previous in vitro study, respiratory capacity measured as state 3 respiration on palmitoyl carnitine was significantly lower in AKIP1-TG compared to WT mice, whereas state 3 respiration on pyruvate remained unaltered. Similar findings were observed for maximal respiration, after addition of FCCP. Mitochondrial DNA damage and oxidative stress markers were not elevated in AKIP1-TG mice and gross mitochondrial morphology was similar. Mitochondrial targeted-proteomics did reveal reductions in mitochondrial proteins involved in energy metabolism. Exercise performance was comparable between genotypes, whereas exercise-induced cardiac hypertrophy was significantly increased in AKIP1-TG mice. After exercise, mitochondrial state 3 respiration on pyruvate substrates was significantly lower in AKIP1-TG compared with WT mice, while respiration on palmitoyl carnitine was not further decreased. This was associated with increased mitochondrial fission on electron microscopy, and the activation of pathways associated with mitochondrial fission and mitophagy. This study suggests that AKIP1 regulates the mitochondrial proteome involved in energy metabolism and promotes mitochondrial turnover after exercise. Future studies are required to unravel the mechanistic underpinnings and whether the mitochondrial changes are required for the AKIP1-induced physiological cardiac growth.

Relative fat mass and prediction of incident atrial fibrillation, heart failure and coronary artery disease in the general population.

BACKGROUND: Relative fat mass (RFM) is an emerging marker of obesity that estimates body fat percentage using a sex-specific formula containing height and waist circumference (WC). We studied the association of RFM with incident atrial fibrillation (AF), heart failure (HF), and coronary artery disease (CAD) and explored RFM cutoffs for cardiovascular disease (CVD) prediction. METHODS: We studied 95,003 participants (age 45 ± 13 years, 59% women) without prevalent AF, HF or CAD from the population-based Lifelines study. Outcomes were ascertained using electrocardiography and self-reported questionnaire data. We used logistic regression to study the association of RFM with individual outcomes and a composite outcome (incident AF, HF, and/or CAD). Multivariable models were adjusted for components of the SCORE risk model (age, sex, systolic blood pressure, cholesterol, and smoking). Optimal cutoffs were determined using the Youden index. RESULTS: During a median follow-up of 3.8 (3.0-4.6) years, 224 (0.2%) participants developed AF, 1003 (1.1%) HF and 657 (0.7%) CAD. After multivariable adjustment, RFM was significantly associated with all outcomes (standardised OR 1.26, 95% CI 1.18-1.34 for the composite outcome). Optimal RFM cutoffs ( ≥26 for men, ≥38 for women) were lower than previously proposed RFM cutoffs ( ≥30 for men, ≥40 for women). In general, overall discriminative ability of RFM and its cutoffs was at least similar (in women) or better (in men) compared to BMI and WC. Since RFM was substantially correlated with age, we additionally determined age-specific cutoffs, which ranged from 23 to 27 in men and 33 to 43 in women. CONCLUSIONS: RFM is associated with incident AF, HF, and CAD and may be used as a simple and intuitive marker of obesity and cardiovascular risk in the general population. This study provides potential RFM cutoffs for CVD prediction that may be used by future studies or preventive strategies targeting obesity and cardiovascular risk.

Diffuse Myocardial Fibrosis on Cardiac Magnetic Resonance Imaging Is Related to Galectin-3 and Predicts Outcome in Heart Failure.

AIMS: Ongoing adverse remodeling is a hallmark of heart failure (HF), which might be reflected by either focal or diffuse myocardial fibrosis. Therefore, in (pre)clinical settings, we used immunohistochemistry or cardiac magnetic resonance imaging (CMR) to investigate the association of (focal or diffuse) fibrosis with cardiac biomarkers and adverse events in HF. METHODS AND RESULTS: In C57Bl/6J mice, we determined the presence and extent of myocardial fibrosis 6 weeks post-myocardial infarction (MI). Furthermore, we studied 159 outpatient HF patients who underwent CMR, and determined focal and diffuse fibrosis by late gadolinium enhancement (LGE) and post-contrast T1 time of the non-LGE myocardium, respectively. HF patients were categorized based on the presence of LGE, and by the median post-contrast T1 time. Kaplan-Meier and Cox regression analyses were used to determine the association of fibrosis with HF hospitalization and all-cause mortality. LGE was detected in 61 (38%) patients. Cardiac biomarker levels were comparable between LGE-positive and LGE-negative patients. LGE-positive patients with a short T1 time had elevated levels of both NT-proBNP and galectin-3 (1611 vs. 453 ng/L, p = 0.026 and 20 vs. 15 µg/L, p = 0.004, respectively). This was not observed in LGE-negative patients. Furthermore, a short T1 time in LGE-positive patients was associated with a higher risk of adverse events (log-rank p = 0.01). CONCLUSION: This study implies that cardiac biomarkers reflect active remodeling of the non-infarcted myocardium of patients with focal myocardial scarring. Diffuse fibrosis, in contrast to focal scarring, might have a higher prognostic value regarding adverse outcomes in HF patients.

Sex-specific aspects of phospholamban cardiomyopathy: The importance and prognostic value of low-voltage electrocardiograms.

BACKGROUND: A pathogenic variant in the gene encoding phospholamban (PLN), a protein that regulates calcium homeostasis of cardiomyocytes, causes PLN cardiomyopathy. It is characterized by a high arrhythmic burden and can progress to severe cardiomyopathy. Risk assessment guides implantable cardioverter-defibrillator therapy and benefits from personalization. Whether sex-specific differences in PLN cardiomyopathy exist is unknown. OBJECTIVE: The purpose of this study was to improve the accuracy of PLN cardiomyopathy diagnosis and risk assessment by investigating sex-specific aspects. METHODS: We analyzed a multicenter cohort of 933 patients (412 male, 521 female) with the PLN p.(Arg14del) pathogenic variant following up on a recently developed PLN risk model. Sex-specific differences in the incidence of risk model components were investigated: low-voltage electrocardiogram (ECG), premature ventricular contractions, negative T waves, and left ventricular ejection fraction. RESULTS: Sustained ventricular arrhythmias (VAs) occurred in 77 males (18.7%) and 61 females (11.7%) (P = .004). Of the 933 cohort members, 287 (31%) had ≥1 low-voltage ECG during follow-up (180 females [63%], 107 males [37%]; P = .006). Female sex, age, age at clinical presentation, and proband status predicted low-voltage ECG during follow-up (area under the curve: 0.78). Sustained VA-free survival was lowest in males with low-voltage ECG (P <.001). CONCLUSION: Low-voltage ECGs predict sustained VA and are a component of the PLN risk model. Low-voltage ECGs are more common in females, yet prognostic value is greater in males. Future studies should determine the impact of this difference on the risk prediction of PLN cardiomyopathy and possibly other cardiomyopathies.

The erythropoietin receptor expressed in skeletal muscle is essential for mitochondrial biogenesis and physiological exercise.

Erythropoietin (EPO) is a haematopoietic hormone that regulates erythropoiesis, but the EPO-receptor (EpoR) is also expressed in non-haematopoietic tissues. Stimulation of the EpoR in cardiac and skeletal muscle provides protection from various forms of pathological stress, but its relevance for normal muscle physiology remains unclear. We aimed to determine the contribution of the tissue-specific EpoR to exercise-induced remodelling of cardiac and skeletal muscle. Baseline phenotyping was performed on left ventricle and m. gastrocnemius of mice that only express the EpoR in haematopoietic tissues (EpoR-tKO). Subsequently, mice were caged in the presence or absence of a running wheel for 4 weeks and exercise performance, cardiac function and histological and molecular markers for physiological adaptation were assessed. While gross morphology of both muscles was normal in EpoR-tKO mice, mitochondrial content in skeletal muscle was decreased by 50%, associated with similar reductions in mitochondrial biogenesis, while mitophagy was unaltered. When subjected to exercise, EpoR-tKO mice ran slower and covered less distance than wild-type (WT) mice (5.5 ± 0.6 vs. 8.0 ± 0.4 km/day, p < 0.01). The impaired exercise performance was paralleled by reductions in myocyte growth and angiogenesis in both muscle types. Our findings indicate that the endogenous EPO-EpoR system controls mitochondrial biogenesis in skeletal muscle. The reductions in mitochondrial content were associated with reduced exercise capacity in response to voluntary exercise, supporting a critical role for the extra-haematopoietic EpoR in exercise performance.