A speckle-tracking strain-based artificial neural network model to differentiate cardiomyopathy type.

Objectives. In heart failure, invasive angiography is often employed to differentiate ischaemic from non-ischaemic cardiomyopathy. We aim to examine the predictive value of echocardiographic strain features alone and in combination with other features to differentiate ischaemic from non-ischaemic cardiomyopathy, using artificial neural network (ANN) and logistic regression modelling. Design. We retrospectively identified 204 consecutive patients with an ejection fraction <50% and a diagnostic angiogram. Patients were categorized as either ischaemic (n = 146) or non-ischaemic cardiomyopathy (n = 58). For each patient, left ventricular strain parameters were obtained. Additionally, regional wall motion abnormality, 13 electrocardiographic (ECG) features and six demographic features were retrieved for analysis. The entire cohort was randomly divided into a derivation and a validation cohort. Using the parameters retrieved, logistic regression and ANN models were developed in the derivation cohort to differentiate ischaemic from non-ischaemic cardiomyopathy, the models were then tested in the validation cohort. Results. A final strain-based ANN model, full feature ANN model and full feature logistic regression model were developed and validated, F1 scores were 0.82, 0.79 and 0.63, respectively. Conclusions. Both ANN models were more accurate at predicting cardiomyopathy type than the logistic regression model. The strain-based ANN model should be validated in other cohorts. This model or similar models could be used to aid the diagnosis of underlying heart failure aetiology in the form of the online calculator (https://cimti.usj.edu.lb/strain/index.html) or built into echocardiogram software.

Artificial neural network-based model enhances risk stratification and reduces non-invasive cardiac stress imaging compared to Diamond-Forrester and Morise risk assessment models: A prospective study.

BACKGROUND: Coronary artery disease (CAD) accounts for more than half of all cardiovascular events. Stress testing remains the cornerstone for non-invasive assessment of patients with possible or known CAD. Clinical utilization reviews show that most patients presenting for evaluation of stable CAD by stress testing are categorized as low risk prior to the test. Attempts to enhance risk stratification of individuals who are sent for stress testing seem to be more in need today. The present study compares artificial neural networks (ANN)-based prediction models to the other risk models being used in practice (the Diamond-Forrester and the Morise models). METHODS: In our study, we prospectively recruited patients who were 19 years of age or older, and were being evaluated for coronary artery disease with imaging-based stress tests. For ANN, the network architecture employed a systematic method, where the number of neurons is changed incrementally, and bootstrapping was performed to evaluate the accuracy of the models. RESULTS: We prospectively enrolled 486 patients. The mean age of patients undergoing stress test was 55.2 ± 11.2 years, 35% were women, and 12% had a positive stress test for ischemic heart disease. When compared to Diamond-Forrester and Morise risk models, the ANN model for predicting ischemia provided higher discriminatory power (DP)(1.61), had a negative predictive value of 98%, Sensitivity 91% [81%-97%], Specificity 65% [60%-79%], positive predictive value 26%, and a potential 59% reduction of non-invasive imaging. CONCLUSION: The ANN models improved risk stratification when compared to the other risk scores (Diamond-Forrester and Morise) with a 98% negative predictive value and a significant potential reduction in non-invasive imaging tests.

In-hospital stroke and mortality trends after left ventricular assist device implantation in the United States from 2017 to 2019.

BACKGROUND: The newer Left Ventricular Assist Device (LVAD), the HeartMate 3 (HM3), was initially approved by the Food and Drug Administration in 2017. We aimed to describe the temporal trends of in-hospital stroke and mortality among patients who underwent LVAD placement between 2017 and 2019. METHODS: The National Inpatient Sample was queried from 2017 to 2019 to identify all adults with heart failure and reduced ejection fraction (HFrEF) who underwent LVAD implantation using the International Classification of Diseases 10th Revision codes. The Cochran-Armitage test was conducted to assess the linear trend of in-hospital stroke and mortality. In addition, multivariable regression analysis was conducted to assess the association of LVAD placement with in-hospital stroke and death. RESULTS: A total of 5,087,280 patients met the selection criteria. Of those, 11,750 (0.2%) underwent LVAD implantation. There was a downtrend in in-hospital mortality per year (trend: -1.8%, p = 0.03), but not in the trend of both ischemic and hemorrhagic stroke per year. LVAD placement was associated with greater odds of stroke of any type (OR = 1.96, 95% CI 1.68-2.29, p < 0.001) and in-hospital mortality (OR = 1.37, 95% CI 1.16-1.61, p < 0.001). CONCLUSIONS: Our study found a significant downtrend in the in-hospital mortality rates among patients with LVAD without substantial changes in stroke rate trends over the study timeframe. As stroke rates remained steady, we hypothesize that improved management along with better control of blood pressure, could have played an important role in survival benefit over the study time frame.

Is Endurance Training Harmful to Older Athletes in the Long Run? An Interesting Case of Exercise-Induced Ventricular Tachycardia.

There is limited data on how endurance training can impact cardiac function and arrhythmogenesis. Intense endurance training has been associated with pathological remodeling of the right ventricle (RV) that can act as a substrate for fatal ventricular arrhythmias in older athletes. A previously healthy 63-year-old female marathon runner presented with symptomatic monomorphic ventricular tachycardia (VT) while exercising. Transthoracic echocardiogram (TTE) demonstrated no structural or functional abnormalities. Electrophysiology study (EPS) with three-dimensional mapping and programmed electrical stimulation was performed demonstrating significant scarring of the RV, including RV outflow tract and RV free wall. VT ablation was successfully performed. Unfortunately, exclusion of arrhythmogenic right ventricular cardiomyopathy (ARVC) was limited due to the lack of cardiac magnetic resonance imaging (MRI). Therefore, a single chamber implantable cardioverter defibrillator (ICD) was placed for secondary prevention. Currently, the clinical significance of exercise-induced ventricular arrhythmias in trained athletes without cardiovascular disease is still unknown. This case highlights the need for investigation with larger studies and longer follow up to help us understand the mechanism of exercise-induced scar formation and standardize our management regarding screening, exercise recommendations, and ICD placement in older athletes.

Severe aortic regurgitation masked as sepsis-induced ARDS in a patient with Streptococcus agalactiae endocarditis.

Septic shock is the most common type of shock in the intensive care unit with an associated mortality close to 50%. Infective endocarditis (IE) is a rare cause of septic shock but carries significant morbidity and mortality. Group B Streptococcus IE (GBS-IE) is an invasive infection with an incidence of approximately 1.7%. It affects immunocompromised patients such as intravenous drug users, alcoholics, those with HIV and elderly among others. IE with severe acute valvular heart disease challenges physicians when assessing fluid status during the early resuscitation in patients with septic shock. We present a case of GBS-IE complicated by severe acute aortic regurgitation with rapidly progressive acute respiratory failure in the setting of septic shock management.

Normalization of biventricular strain post steroid treatment of effusive constrictive pericarditis.

Peak left ventricular strain measured by speckle tracking echocardiography has previously been shown to normalize following pericardectomy in constrictive pericarditis, as indicated by an increase of the strain ratio between the lateral wall and septum. Here we present a case of effusive constrictive pericarditis treated with corticosteroids. Pre-treatment we observed reduced contractility of the lateral walls of both ventricles as measured by peak strain, with sparing of overall septal function, but with hypercontractility of the basal septal segment. Septal and lateral wall function normalized with corticosteroid treatment. Our observations from this case prompts investigation into the value of lateral/septal wall strain ratios in both ventricles for quantitatively monitoring the response of constrictive pericarditis to medical therapy. .

The relationship between fasting blood glucose variability and coronary artery collateral formation in type 2 diabetes patients with coronary artery disease.

BACKGROUND: Coronary collaterals are an alternative source of blood supply to ischemic myocardium. Well-developed coronary collateral arteries in patients with coronary artery disease (CAD) limit the size of acute myocardial infarction and improves survival. The aim of this study was to investigate the relationship between glycemic variability and coronary collateral formation in patients with type 2 diabetes mellitus and CAD. METHODS: Consecutive patients undergoing percutaneous coronary intervention or coronary artery bypass grafting procedures were studied. Multivariate logistic regression models were used to examine the association between coronary artery collateral formation graded by Rentrope classification and glycemic variability, measured by coefficient variation of fasting blood glucose. RESULTS: In our study, we retrospectively enrolled 300 patients, of whom 239 were diabetic (age: 70.1±11.9, 56% men) and 61 were nondiabetic (age: 71.5±11.5, 72% men). Diabetic patients were further stratified as follows: those with poor coronary collateral artery development (n=171, age: 69.7±12.4, 55% men) and those with good coronary collateral artery development (n=68, age 71.1±10.8, 59% men) according to the Rentrope classification. Our findings did not show association between glycemic variability and coronary collateral vessels development after controlling for potential confounders (odds ratio: 2.51; 95% confidence interval: 0.57-11.03; P=0.22). The culprit lesion (≥75% stenosis) in the left anterior descending artery and the right coronary artery was more frequent in the good collateral group compared with the poor collateral group (66 vs. 50%, P=0.02; 63 vs. 45%, P=0.01 respectively). CONCLUSION: Glycemic variability is not associated with coronary collateral artery formation in patients with type 2 diabetes mellitus and CAD.