Search

Aims: Takotsubo syndrome (TTS) is associated with a substantial rate of adverse events. We sought to design a machine learning (ML)-based model to predict the risk of in-hospital death and to perform a clustering of TTS patients to identify different risk profiles., Methods and Results: A ridge logistic regression-based ML model for predicting in-hospital death was developed on 3482 TTS patients from the International Takotsubo (InterTAK) Registry, randomly split in a train and an internal validation cohort (75% and 25% of the sample size, respectively) and evaluated in an external validation cohort (1037 patients). Thirty-one clinically relevant variables were included in the prediction model. Model performance represented the primary endpoint and was assessed according to area under the curve (AUC), sensitivity and specificity. As secondary endpoint, a K-medoids clustering algorithm was designed to stratify patients into phenotypic groups based on the 10 most relevant features emerging from the main model. The overall incidence of in-hospital death was 5.2%. The InterTAK-ML model showed an AUC of 0.89 (0.85-0.92), a sensitivity of 0.85 (0.78-0.95) and a specificity of 0.76 (0.74-0.79) in the internal validation cohort and an AUC of 0.82 (0.73-0.91), a sensitivity of 0.74 (0.61-0.87) and a specificity of 0.79 (0.77-0.81) in the external cohort for in-hospital death prediction. By exploiting the 10 variables showing the highest feature importance, TTS patients were clustered into six groups associated with different risks of in-hospital death (28.8% vs. 15.5% vs. 5.4% vs. 1.0.8% vs. 0.5%) which were consistent also in the external cohort., Conclusion: A ML-based approach for the identification of TTS patients at risk of adverse short-term prognosis is feasible and effective. The InterTAK-ML model showed unprecedented discriminative capability for the prediction of in-hospital death., (© 2023 The Authors. European Journal of Heart Failure published by John Wiley & Sons Ltd on behalf of European Society of Cardiology.)

The impact of right ventricular impairment (RVI) on the morbidity and mortality of patients with Takotsubo syndrome (TTS) is well-debated. We conducted a meta-analysis to evaluate the mortality and morbidity risk associated with RVI compared with those without RVI in patients with TTS. A comprehensive search was performed in PubMed and Embase from inception to April 19, 2019. Our primary outcome of interest was in-hospital and long-term mortality. Other outcomes of interest were acute heart failure, left ventricular systolic function, tricuspid and mitral regurgitation, and length of hospital stay (LOS). We are reporting our outcomes as a cumulative odds ratio (OR). After an initial search, 10 studies with 1210 subjects were included in the quantitative analysis. Mean follow-up was 31 months. The odds of in-hospital and long-term mortality in TTS patients with and without RVI were not significantly different (p = 0.13 and 0.40). In TTS patients without RVI, the odds of acute heart failure, and mitral and tricuspid regurgitation were significantly lower at an OR of 0.26 (p < 0.0001), 0.40 (p = 0.0001), and 0.52 (p = 0.02) respectively. TTS patients with RVI had significantly lower mean LVEF (34% vs 41%, p = 0.03) and numerically higher mean LOS (9.5 days vs 7.6 days, p = 0.52) compared with those without RVI. The presence of RVI represents a severe form of TTS disease spectrum, characterized by severely reduced LVEF, higher incidence of MR and presence of TR. Although there was a trend toward increased in-hospital and long-term mortality, RVI in TTS does not portend worse survival., (© 2020. Springer Science+Business Media, LLC, part of Springer Nature.)

Up to one-third of patients selected by current guidelines do not respond to cardiac resynchronization therapy (CRT), the aim of this study was to find out novel analytical approaches to improve pre-implantation CRT response prediction. Among 31 pre-implantation features of clinical, laboratory, electrocardiography (ECG), and echocardiography variables in a consecutive cohort of patients receiving a first-time CRT device (CRT-pacemaker or CRT-defibrillator), we developed a machine learning (ML) model with three classification algorithms (support vector machines (SVM), K nearest neighbors, and random subspaces) with the best features combination to predict CRT response. Three categorical variables, left bundle branch block (LBBB), nonischemic cardiomyopathy, and female gender, were independently associated with CRT responses. Among continuous variables, including septal wall thickness, posterior wall thickness, and relative wall thickness (RWT), could regularize ECG QRS duration (QRSd) and significantly enhance the correlation between QRSd and CRT response. The 3 ML algorithms in a total of 38 features combinations constantly recognized that the features combined with QRSd/RWT outperformed the combinations without it. For each of three algorithms, the triplet feature combination of QRSd/RWT, LBBB, and nonischemic cardiomyopathy repeatedly increased the classification rate more than 8%. The best performance for CRT response prediction occurred with SVM model, which proposed actual QRSd/RWT values that favored CRT responses in patients both with and without LBBB. Lower QRSd/RWT values were required for CRT responses in patients with ischemic cardiomyopathy compared to those with non-ischemic cardiomyopathy. ML from ventricular remodeling characteristics-regularized QRSd improves CRT response prediction.

Acutely decompensated heart failure (HF), one of the most common reasons for hospitalization, places an intense economic pressure on the health care system and adversely affects outcome of HF patients. Due to lack of reliable clinical tools to assess and monitor hemodynamics, accurate judgment on cardiac preload remains a challenge and complicates current inpatient HF management. In this review, we discuss the emerging role of real-time quantitative Doppler echocardiography (DE) in identifying inappropriate cardiac preload, monitoring volume status during the management, and improving quality of care in patients with acute HF. We illustrate the utilization of DE in common clinical scenarios, propose stepwise algorithms to effectively utilize serial quantitative DE in the bedside care, and discuss obstacles and prospects of quantitative DE utilization in HF management. These efforts will further prompt the development of multi-center prospective studies to define and validate the specific roles of quantitative DE in reducing hospitalization time and improving outcome of HF patients., (© The European Society of Cardiology 2015.)

Heart failure constitutes a significant source of morbidity and mortality in the United States and its incidence and prevalence continue to grow, increasing its burden on the health care system. Renal dysfunction in patients with heart failure is common and has been associated with adverse clinical outcomes. This complex interaction is characterized by a pathophysiological disequilibrium between the heart and the kidney, in which cardiac malfunction promotes renal impairment, which in turn feeds back for further deterioration of cardiovascular function. Multiple neurohumoral and hemodynamic mechanisms are involved in this cardiorenal dyshomeostasis, including the deficiency of and/or resistance to compensatory natriuretic peptides, leading to sodium retention, volume overload and organ remodeling. Management of patients with cardiorenal dysfunction can be challenging and should be individualized. Emerging therapies must address the impairment of both organs to secure better clinical outcomes. To this end, a multidisciplinary approach is warranted to achieve optimal results.

Heart failure constitutes a significant source of morbidity and mortality in the United States, and its incidence and prevalence continue to grow, increasing its burden on the healthcare system. Renal dysfunction in patients with heart failure is common and has been associated with adverse clinical outcomes. This interaction, termed the cardiorenal syndrome, is a complex phenomenon characterized by a pathophysiologic disequilibrium between the heart and the kidney, in which malfunction of 1 organ consequently promotes the impairment of the other. Multiple neurohumoral mechanisms are involved in this cardiorenal interaction, including the deficiency of and/or resistance to compensatory natriuretic peptides, leading to sodium retention, volume overload and organ remodeling. Management of patients with the cardiorenal syndrome can be challenging and should be individualized. Emerging therapies must address the function of both organs to secure better clinical outcomes. To this end, a multidisciplinary approach is recommended to achieve optimal results.

A letter to the editor is presented in response to the article on estimating the diagnostic accuracy of Doppler echocardiography (DE) to assess pulmonary arterial systolic pressure (PASP) and diagnose pulmonary hypertension (PH) on the December 10, 2012 issue.

Abstract Background In patients with acute anterior myocardial infarction (MI), sometimes an "apical ballooning" contractile dysfunction pattern that exceeds factual myocardial injury is identified in the ventriculography and bedside echocardiography. The hemodynamic consequences/sequela of this "Tako-tsobu effect" has not been well delineated. Of note, this anatomic imaging finding often misleads frontline physicians who assume reciprocal causation of persistent cardiac pump failure and ventricular pressure overload. Methods and results Using real-time myocardial perfusion contrast echocardiography (MCE), we investigated myocardial (microvascular) perfusion in 60 patients after acute MI and coronary revascularization. Twenty-eight percent of the studied patients showed significantly mismatched myocardial perfusion and contractile defects. In these patients, an integrated imaging assessment with coronary angiography/ventriculography, deformation echocardiography, and MCE proved that the myocardial mechanic abnormalities significantly exceeded the defected perfusion areas. Compared with 72% of the patients without perfusion-contractility mismatch, apparently worse systolic functions (left ventricular ejection, wall motion score, and systolic longitudinal strain) in these patients did not change diastolic ventricular filling pressures (E/E′ and E/A) or hemodynamic consequences/adverse events. Both systolic and diastolic functions in patients with perfusion-contractility mismatch appeared to be comparable with those in patients with Tako-tsubo syndrome. Conclusions Real-time MCE identifies discrepant myocardial microvascular perfusion and mechanics in patients with acute MI. The "Tako-tsubo effect" in patients with perfusion-contractility mismatch does not cause diastolic filling pressure change or worse hemodynamic consequence/cardiac event. Highlights • "Tako-tsobu effect" in myocardial infarction results in an assumption of reciprocal causation of pump failure and ventricular pressure overload. • Myocardial perfusion echocardiography identifies discrepant myocardial microvascular perfusion and mechanics in "Tako-tsobu effect". • "Worse" systolic dysfunctions in patients with "Tako-tsobu effect" do not deteriorate hemodynamics or increase adverse cardiac events. • Identifying discordant changes between ventricular contractile function and filling pressure helps post-myocardial infarction management. [ABSTRACT FROM AUTHOR]