Left-ventricular mechanical dyssynchrony in the prognosis of dilated cardiomyopathy: Which parameter is more useful?

A method using deep learning to discover new predictors from left-ventricular mechanical dyssynchrony for CRT response

BACKGROUND

Studies have shown that the conventional parameters characterizing left ventricular mechanical dyssynchrony (LVMD) measured on gated SPECT myocardial perfusion imaging (MPI) have their own statistical limitations in predicting cardiac resynchronization therapy (CRT) response. The purpose of this study is to discover new predictors from the polarmaps of LVMD by deep learning to help select heart failure patients with a high likelihood of response to CRT.

METHODS

One hundred and fifty-seven patients who underwent rest gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at 6 [Formula: see text] 1 month follow up. The autoencoder (AE) technique, an unsupervised deep learning method, was applied to the polarmaps of LVMD to extract new predictors characterizing LVMD. Pearson correlation analysis was used to explain the relationships between new predictors and existing clinical parameters. Patients from the IAEA VISION-CRT trial were used for an external validation. Heatmaps were used to interpret the AE-extracted feature.

RESULTS

Complete data were obtained in 130 patients, and 68.5% of them were classified as CRT responders. After variable selection by feature importance ranking and correlation analysis, one AE-extracted LVMD predictor was included in the statistical analysis. This new AE-extracted LVMD predictor showed statistical significance in the univariate (OR 2.00, P = .026) and multivariate (OR 1.11, P = .021) analyses, respectively. Moreover, the new AE-extracted LVMD predictor not only had incremental value over PBW and significant clinical variables, including QRS duration and left ventricular end-systolic volume (AUC 0.74 vs 0.72, LH 7.33, P = .007), but also showed encouraging predictive value in the 165 patients from the IAEA VISION-CRT trial (P < .1). The heatmaps for calculation of the AE-extracted predictor showed higher weights on the anterior, lateral, and inferior myocardial walls, which are recommended as LV pacing sites in clinical practice.

CONCLUSIONS

AE techniques have significant value in the discovery of new clinical predictors. The new AE-extracted LVMD predictor extracted from the baseline gated SPECT MPI has the potential to improve the prediction of CRT response.

Incremental value of left ventricular shape parameters measured by gated SPECT MPI in predicting the super-response to CRT

BACKGROUND

The purpose of this study was to evaluate the predictive value of left ventricular (LV) shape parameters measured by gated SPECT myocardial perfusion imaging (MPI) in super-responders enrolled in the VISION-CRT trial.

METHODS

One hundred and ninety-nine patients who met standard criteria for CRT from multiple centers were enrolled in this study. End-systolic eccentricity (ESE) and end-diastolic eccentricity (EDE) were measures of LV shape. Super-responders were the patients who had a relative increase in left ventricular ejection fraction (LVEF) ≥ 15%.

RESULTS

Complete data were obtained in 165 patients, and 43.6% of them were classified as super-responders. ESE was an independent predictor of CRT super-responders in univariate (OR 12.59, 95% CI 1.56-101.35, P = .017) and multivariate analysis (OR 35.71, 95% CI 1.66-766.03, P = .006). ESE had an incremental value over significant clinical and SPECT imaging variables, including angiotensin-converting enzyme inhibitors or angiotensin II receptor blocker, coronary artery disease, myocardial infarction, LVEF, end-diastolic volume index, and scar burden (AUC 0.82 vs. 0.80, sensitivity 0.68 vs. 0.65, specificity 0.82 vs. 0.78).

CONCLUSIONS

LV shape parameters derived from gated SPECT MPI have the promise to improve the prediction of the super-response to CRT. Moreover, ESE provides incremental value over existing clinical and nuclear imaging variables.

Prognostic value of integrative analysis of electrical and mechanical dyssynchrony in patients with acute heart failure

BACKGROUND

Left ventricular mechanical dyssynchrony has been shown to provide significant clinical values for chronic heart failure (HF) and cardiac resynchronization therapy (CRT). The purpose of this study was to evaluate whether electrical dyssynchrony combined with mechanical dyssynchrony has an incremental benefit over electrical dyssynchrony or mechanical dyssynchrony alone to predict clinical events in patients with acute heart failure (AHF).

METHODS

Ninety-six AHF patients who received standard 12-lead ECG, gated single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI), and echocardiography were enrolled. Thirty-two normal subjects were collected as the control group to get the normal database of mechanical dyssynchrony. The end point is the composite of all-cause death and heart transplantation. Electrical dyssynchrony was defined as QRS duration > 120 ms. Mechanical dyssynchrony was defined as > mean + 2 × SD phase standard deviation (PSD) or phase bandwidth (PBW) based on our normal database.

RESULTS

During the follow-up of 28 ± 10 months, complete data were obtained in 92 patients. 26 (28.3%) Patients who reached the end point were classified into the event group. There were no significant differences in PSD or PBW between the event and non-event groups. However, PBW > 77.76° was independently associated with the end point in the univariate and multivariate analysis (hazard ratio 2.92, 95% confidence interval 1.00-8.47, P = .049; hazard ratio 3.89, 95% confidence interval 1.01-14.97, P = .048). The Kaplan-Meier curve with a log-rank test showed that the end point rate was significantly higher in the patients with PBW > 77.76° (log-rank P = .039). Moreover, the ROC curve analysis showed that the area under the curve (AUC) for predicting end point events by the integrative analysis of QRS > 120 ms and PBW > 77.76° was significantly improved compared to QRS duration > 120 ms (AUC: 0.75 vs 0.68, P = .001) or PBW > 77.76° (AUC: 0.75 vs 0.62, P = .049), respectively. The model of combined electrical and mechanical dyssynchrony yielded a further significantly improved risk prediction for adverse events in the global χ2.

CONCLUSIONS

The combination of QRS duration > 120 ms and PBW > 77.76° was an independent predictor of all-cause death and heart transplantation in AHF patients. The integrative analysis of electrical and mechanical dyssynchrony provides incremental prognostic value for clinical use.

Prognostic value of left-ventricular systolic and diastolic dyssynchrony measured from gated SPECT MPI in patients with dilated cardiomyopathy

BACKGROUND

Left-ventricular systolic dyssynchrony (LVSD) has been an important prognostic factor in the patients with dilated cardiomyopathy (DCM). However, the association between the LV diastolic dyssynchrony (LVDD) and clinical outcome is not well established. This study aims to evaluate the prognostic values of both systolic and diastolic dyssynchrony in patients with DCM.

METHODS

Fifty-two patients with DCM were enrolled and divided into two groups according to cardiac deaths from the follow-up data. The phase-analysis technique was applied on resting gated short-axis SPECT MPI images to measure LV systolic and diastolic dyssynchrony, including phase standard deviation (PSD), phase histogram bandwidth (PBW), and phase entropy (PE). Variables with P < 0.10 in the univariate analysis were included in the multivariate cox analysis.

RESULTS

During the follow-up period (2.9 ± 1.7 years), 18 (34.6%) cardiac deaths were observed. Compared with survivors, patients with cardiac death had lower LVEF (P = 0.011), and more severe LV systolic and diastolic dyssynchrony. The univariate cox regression analysis showed that hypertension, NT-proBNP, LVEF, systolic PSD, systolic PE, and diastolic PBW were statistically significantly associated with cardiac death. The multivariate cox regression analysis showed that systolic PE and diastolic PE were independent predictive factors for cardiac death. Furthermore, the receiver operating characteristic (ROC) analysis, when applied into the combination of systolic PE and diastolic PE for predicting cardiac death, had an area under curve (AUC) of 0.766, a sensitivity of 0.765, and a specificity of 0.722.

CONCLUSIONS

Both the LVSD and LVDD parameters from SPECT MPI have important prognostic values for DCM patients. Both systolic PE and diastolic PE are independent prognostic factors for cardiac death.