High-risk inferior myocardial infarction: Can speckle tracking predict proximal right coronary lesions?

A visually interpretable detection method combines 3-D ECG with a multi-VGG neural network for myocardial infarction identification

BACKGROUND AND OBJECTIVE

The automatic recognition of myocardial infarction (MI) by artificial intelligence (AI) has been an emerging topic of academic research and an existing classification method that can recognize conventional electrocardiogram (ECG) signals with high accuracy. However, they are employed to classify one-dimensional (1-D) ECG signals rather than three-dimensional (3-D) ECG images, and it is limited to provide physicians with significant recommendations to aid in diagnosis like highlighting abnormal leads. Other studies on 3-D ECG images either did not achieve high accuracy or did not employ an inter-patient classification scheme. By proposing a multi-VGG deep neural network, this study aims to develop an automatic classification method for identifying myocardial infarction with inter-patient high accuracy and proper interpretability using 3-D ECG image and a Grad-CAM++ method.

METHODS

We apply a multi-VGG deep convolutional neural network to top-view images of 3-D ECG, which are generated from simply denoised standard 12 leads ECG signals for classification. The multi-network method, which separately classifies QRS areas, ST areas, and whole heartbeats, was applied to improve classification performance. Furthermore, the Grad-CAM++ method was used to provide visually interpretable heatmaps for user's attention to improve network interpretability and assist physicians in MI diagnosis RESULTS: The proposed method achieved 95.65% inter-patient accuracy and exactly perfect inner-patient accuracy in the Physikalisch-Technische Bundesanstalt (PTB) diagnostic ECG database experiment. In the PTB-XL diagnostic ECG database, the proposed method achieved 97.23% inter-patient accuracy. The Grad-CAM++ experiment results also showed that the highlighted areas matched the medical diagnosis criteria for myocardial infarction.

CONCLUSIONS

Our method demonstrates that 3-D ECG images with AI classification can be efficiently employed for heart disease diagnosis with both high accuracy and visual interpretability.

Role of 2-dimensional speckle tracking echocardiography in diagnosis of right ventricular involvement in patients with inferior wall myocardial infarction undergoing primary percutaneous coronary intervention

Diagnosis of right ventricular (RV) infarction in the setting of acute inferior wall myocardial infarction (IWMI) has important prognostic implications. We sought to assess the role of 2-D speckle tracking echocardiography (2-D STE) for the assessment of RV involvement in acute IWMI. We included 100 consecutive patients with a diagnosis of recent IWMI, of which 73 had an RCA culprit lesion, undergoing primary percutaneous coronary intervention (PPCI). Patients (n = 73) were classified into 2 groups based on angiographic evidence of RV involvement (lesions proximal to or involving RV branch versus distal lesions). Echocardiographic features of RV dysfunction were assessed using conventional 2-D echocardiographic, and Tissue Doppler parameters as well as 2-D speckle tracking echocardiography. Out of the 73 patients, 42 had RCA lesion proximal to or involving RV branch, while 31 patients had RCA culprit distal to RV branch. Among different parameters assessing RV function, only RV-FWLS was significantly lower among the former group (- 14.2 ± 4.6 vs. - 17.7 ± 4.2, p = 0.026). Receiver-operator characteristic (ROC) analysis showed that RV-FWLS had the strongest discriminatory capability to identify RV infarction (AUC = 0.7, p = 0.02, 95% CI  0.53-0.78). A cut-off value of RV-FWLS ≤ - 20.5% had 88% sensitivity and 33% specificity for diagnosis of RV infarction. STE-derived RV-FWLS with cutoff ≤ - 20.5% could be a reliable and promising tool for prediction of RV involvement in the setting of acute IWMI, which could guide proper risk stratification and tailored acute management strategy.

Association of GDF-15 and Syntax Score in Patient with Acute Myocardial Infarction

Aims

GDF-15 is considered to be an important biomarker for cardiovascular events, but the differences in serum GDF-15 levels between acute myocardial infarction (AMI) patients and non-AMI patients warrant further investigation.

Methods

A cohort of 409 subjects was enrolled in the current study. The Syntax score was calculated from the baseline coronary angiography results by using online methods. Blood samples were obtained at the start of the study for an assessment of GDF-15 by using ELISA methods.

Results

Patients with AMI had significantly higher levels of serum GDF-15 (Wilcox test, P < 0.001), Syntax scores (Wilcox test, P = 0.006), and left ventricular ejection fractions (LEVF, Wilcox test, P< 0.001). However, no significant differences were present among the other clinical characteristics. The logistical regression analysis indicated that serum GDF-15 levels (P=0.01534) were independent predictors of non-AMI and AMI after adjusting for age, sex, smoking status, and LVEF.

Conclusions

Elevated serum levels of GDF-15 are independently associated with the risk of MI, and GDF-15 may serve as a protective factor for MI in the cardiovascular system.

Age- and gender-related normal references of right ventricular strain values by tissue tracking cardiac magnetic resonance: results from a Chinese population

Background

Myocardial deformation is a sensitive marker for sub-clinical myocardial dysfunction and carries independent prognostic significance across a broad range of cardiovascular diseases. Reproducible and repeatable assessment of right ventricular (RV) function is vital for monitoring congenital and acquired heart diseases. The purpose of this study was to determine the normal references of RV strain and strain rate values using tissue tracking cardiac magnetic resonance imaging (MRI).

Methods

A cohort of 120 normal human subjects from each decade of life between 20 and 70 without cardiac diseases were enrolled in this study. Retrospectively, electrocardiogram (ECG) gating cardiac MRI imaging was performed at 3.0T with balanced steady-state free precession (bSSFP) imaging. RV global and segmental myocardial strains were analyzed by tissue tracking by two experienced observers.

Results

The global peak longitudinal strain (GLS) and global peak radial strain (GRS) was -24.3±4.7 and 23.0±8.5 respectively. For the peak circumferential strains (GCS), the values for global, basal, mid-cavity, and apical segments were -13.3±4.1, -13.1±4.0, -12.5±4.7, and -15.9±5.8, respectively. There were significant gender differences in peak GRS (P=0.009) and at the base (P=0.017) and the mid-cavity (P=0.011) with greater deformation in females than in males. There were also significant age differences in GRS (P<0.001), GCS for basal (P<0.001), and mid-cavity segments (P=0.037). On Bland-Altman analysis, peak GLS and GRS had the best intra-observer agreement (mean bias, -0.13±0.51; 95% CI, -1.13-0.87) and inter-observer (mean bias, 0.054±0.31; 95% CI, -0.55-0.66) agreement, respectively.

Conclusions

Normal values of RV deformation for healthy individuals using tissue tracking cardiac magnetic resonance (CMR-TT) provided good RV peak strain reproducibility. There was a significant correlation between RV strain or strain rate parameters with either age or sex.

Acute right ventricular myocardial infarction

INTRODUCTION

Acute right ventricular myocardial infarction (RVMI) is observed in 30-50% of patients presenting with inferior wall myocardial infarction (MI) and, occasionally, with anterior wall MI. The clinical consequences vary from no hemodynamic compromise to severe hypotension and cardiogenic shock depending on the extent of RV ischemia. Areas covered: The pathophysiological mechanisms, diagnostic steps, and novel therapeutic approaches of acute RVMI are described. Expert commentary: Diagnosis of acute RVMI is based on physical examination, cardiac biomarkers, electrocardiography, and coronary angiography, whereas noninvasive imaging modalities (echocardiography, cardiac magnetic resonance imaging) play a complementary role. Early revascularization, percutaneous or pharmacological, represents key step in the management of RMVI. Maintenance of reasonable heart rate and atrioventricular synchrony is essential to sustain adequate cardiac output in these patients. When conventional treatment is not successful, mechanical circulatory support, including right ventricle assist devices, percutaneous cardiopulmonary support, and intra-aortic balloon pump, might be considered. The prognosis associated with RVMI is worse in the short term, compared to non-RVMI, but those patients who survive hospitalization have a relatively good long-term prognosis.

High-risk inferior myocardial infarction: Can speckle tracking predict proximal right coronary lesions?

BACKGROUND

It is important to diagnose right ventricular (RV) infarction in the setting of acute inferior myocardial infarction (MI). We aimed to improve the diagnostic accuracy of RV infarction and identify a high-risk subset of inferior MI patients with proximal RCA lesions.

HYPOTHESIS

We tried to find the link between speckle tracking and coronaries in high risk inferior infarction METHODS: This study included 68 patients within 24 hours of first acute inferior MI. Group 1 (n = 49) isolated inferior MI; group 2 (n = 19) inferior and RV MI. echocardiography for RV free wall longitudinal strain (FWLS), RV fractional area change (FAC), tricuspid annular plane systolic excursion (TAPSE), RV myocardial performance index (MPI) and peak systolic velocity (S').

RESULTS

Group 2 had higher MPI by tissue Doppler and 2D-RV average FWLS, whereas RV FAC, S', and TAPSE were lower (P < 0.001). In group 1, 14.4% had a significant proximal RCA lesion with impaired RV function. RV average FWLS at a cutoff value ≥ - 19.7% can predict proximal RCA culprit lesion with 91.7% sensitivity and 70.5% specificity, which was detected as an independent predictor in multivariate logistic regression (odds ratio: 37.75, P = 0.036).

CONCLUSIONS

2D RV average FWLS at a cutoff of ≥ - 19.7% is a useful added tool for diagnosis of RV involvement and an independent predictor to rule in proximal RCA culprit lesion in inferior-wall MI patients in the emergency department.