Speckle-Tracking Echocardiography Predicts Adverse Left Ventricular Remodeling After Valve Replacement in Rheumatic Mitral Stenosis.

Background: Rheumatic mitral stenosis(RMS) may leads to left ventricular remodeling (LVR), which can persist even after valve surgery. Identifying markers for early structure and function in patients with rheumatic heart disease who are at risk for adverse LVR after surgery can help determine the optimal timing of intervention. This study aimed to investigate whether preoperative parameters of global left ventricular long-axis strain (LVGLS) and mechanical discretization (MD) could predict postoperative adverse LVR. Methods: A total of 109 adult patients with RMS and 50 healthy controls were enrolled in this study. Baseline clinical features, conventional echocardiography results, LVGLS, and MD were compared between the two groups. Pre- and post-surgery echocardiography measurements were collected, and adverse LVR was defined as a>15% increase in left ventricular end-diastolic volume or >10% decrease in left ventricular ejection fraction. Binary regression analysis was used to determine independent predictors of poor left ventricular remodeling. Results: The variables associated with adverse LVR in this study were LVGLS (P<0.001, odds ratio: 1.996, 95% CI: 1.394-2.856) and MD (P=0.011, odds ratio: 1.031, 95% CI: 1.007-1.055). The poorly reconstructed group had lower absolute values of LVGLS and higher MD than the healthy control group and the non-poorly reconstructed group. A LVGLS cutoff of -15.0% was the best predictor for patients with poorly reconstructed LVR (sensitivity: 75.7%; specificity: 100.0%; AUC: 0.93), and a MD cutoff of 63.8ms was the best predictor (sensitivity: 63.8%; specificity: 98.6%; AUC: 0.88). Conclusion: Speckle tracking echocardiography has potential value for predicting the progression of adverse LVR and for identifying non-responders among patients with RMS undergoing surgery.

Deep learn-based computer-assisted transthoracic echocardiography: approach to the diagnosis of cardiac amyloidosis.

Myocardial amyloidosis (CA) differs from other etiological pathologies of left ventricular hypertrophy in that transthoracic echocardiography is challenging to assess the texture features based on human visual observation. There are few studies on myocardial texture based on echocardiography. Therefore, this paper proposes an adaptive machine learning method based on ultrasonic image texture features to identify CA. In this retrospective study, a total of 289 participants (50 cases of myocardial amyloidosis; Hypertrophic cardiomyopathy: 70 cases; Uremic cardiomyopathy: 92 cases; Hypertensive heart disease: 77 cases). We extracted the myocardial ultrasonic imaging features of these patients and screened the features, and four models of random forest (RF), support vector machine (SVM), logistic regression (LR) and gradient decision-making lifting tree (GBDT) were established to distinguish myocardial amyloidosis from other diseases. Finally, the diagnostic efficiency of the model was evaluated and compared with the traditional ultrasonic diagnostic methods. In the overall population, the four machine learning models we established could effectively distinguish CA from nonCA diseases, AUC (RF 0.77, SVM 0.81, LR 0.81, GBDT 0.71). The LR model had the best diagnostic efficiency with recall, F1-score, sensitivity and specificity of 0.21, 0.34, 0.21 and 1.0, respectively. Slightly better than the traditional ultrasonic diagnosis model. In further subgroup analysis, the myocardial amyloidosis group was compared one-by-one with the patients with hypertrophic cardiomyopathy, uremic cardiomyopathy, and hypertensive heart disease groups, and the same method was used for feature extraction and data modeling. The diagnostic efficiency of the model was further improved. Notably, in identifying of the CA group and HHD group, AUC values reached more than 0.92, accuracy reached more than 0.87, sensitivity equal to or greater than 0.81, specificity 0.91, and F1 score higher than 0.84. This novel method based on echocardiography combined with machine learning may have the potential to be used in the diagnosis of CA.

Visceral fat index/percentage body fat ratio is independently associated with proximal aortic dilatation in a middle-aged and aged Chinese population in Liujiang of Guangxi.

BACKGROUND AND AIMS: Increased volume of visceral adipose tissue is associated with worsening of cardiovascular disease risk factors that contribute to aortic dilatation. We investigated the effects of visceral fat index (VFI) and VFI/percentage body fat (PBF) ratio on proximal aortic size and proximal aortic dilatation (PAD), to assess whether excess visceral fat deposition is an independent risk factor for PAD. METHODS: 738 participants aged 35 years or more were included in this cross-sectional survey. The sizes of aortic valve annulus (AVA), sinuses of Valsalva (SV), sinotubular junction (STJ), and ascending aorta (AscAo) were measured by transthoracic ultrasound. Multivariate linear regression, binary logistic regression, Bayesian linear regression, and receiver operating characteristic curves were performed to clarify the effects of VFI and VFI/PBF ratio on PAD. RESULTS: There were 78 participants (10.6%) with PAD. VFI and VFI/PBF ratio in the population with PAD was significantly increased, compared to the population without PAD (p < 0.001). However, PBF was not significantly different between the two populations. VFI/PBF ratio was positively associated with sizes of AVA, SV, STJ, and AscAo (p < 0.05), and was independently related to PAD (p < 0.05). A 1-SD increment in VFI/PBF ratio was associated with 13.35-fold increased risk of PAD (odds ratio: 13.35, p < 0.05). CONCLUSIONS: VFI/PBF ratio is independently associated with PAD. An increased proportion of visceral fat may contribute to PAD. VFI/PBF ratio calculation may be used for the preliminary identification of individuals at high risk of PAD in the Chinese population.