The combined assessment of TWA and LP was associated with a high positive predictive value for an arrhythmic event after acute MI. Therefore, it could be a useful index to identify patients at high risk of arrhythmic events.

Late potentials are a noninvasive risk stratifier in patients with Brugada syndrome. These results may support the idea that conduction disturbance per se is arrhythmogenic.

SUMMARYMicrovolt T-wave alternans (TWA) and QT interval dispersion (QTD), which reflect temporal and spatial repolarization abnormalities, respectively, have been proposed as useful indices to identify patients at risk for ventricular tachyarrhythmias (VTs). The purpose of this study was to clarify which repolarization abnormality marker is more useful in predicting arrhythmic events in patients with dilated cardiomyopathy (DCM).Forty-two consecutive nonischemic DCM patients underwent the assessment of TWA and QTD. Patients undergoing antiarrhythmic pharmacotherapy, except β-blockers and those with irregular basic rhythms, were excluded from entry. Eight patients were also excluded because of indeterminate test results. Therefore, 34 DCM patients were prospectively assessed. The end point of the study was the documentation of VT defined as ≥ 5 consecutive ectopic beats during the follow-up period.TWA and QTD (≥65 msec) were positive in 24 (80%) and 11 (37%) of 30 patients with available follow-up data, respectively. There was no relationship between TWA and QTD. During a follow-up of 13±11 months, VTs occurred in 13 patients (43%). In Cox regression analysis, TWA was a significant risk stratifier (p=0.02), whereas QTD was not. The sensitivity, specificity, and positive and negative predictive values of TWA in predicting VTs were 100%, 35%, 54%, and 100%, respectively.TWA could be a useful noninvasive index to identify patients at risk for VTs in the setting of DCM. This study may suggest that temporal repolarization abnormality is associated more with arrhythmogenesis than with spatial repolarization abnormality in DCM patients. (Jpn Heart J 2001; 42: 451-457)

Background: Radiofrequency catheter ablation (RFCA) is an effective therapy for atrial fibrillation (AF). However, it the problem of AF recurrence remains. This study investigates whether a deep convolutional neural network (CNN) can accurately predict AF recurrence in patients with AF who underwent RFCA, and compares CNN with conventional statistical analysis.Methods and Results: Three-hundred and ten patients with AF after RFCA treatment, including 94 patients with AF recurrence, were enrolled. Nine variables are identified as candidate predictors by univariate Cox proportional hazards regression (CPH). A CNNSurv model for AF recurrence prediction was proposed. The model's discrimination ability is validated by a 10-fold cross validation method and measured by C-index. After back elimination, 4 predictors are used for model development, they are N-terminal pro-BNP (NT-proBNP), paroxysmal AF (PAF), left atrial appendage volume (LAAV) and left atrial volume (LAV). The average testing C-index is 0.76 (0.72-0.79). The corresponding calibration plot appears to fit well to a diagonal, and the P value of the Hosmer-Lemeshow test also indicates the proposed model has good calibration ability. The proposed model has superior performance compared with the DeepSurv and multivariate CPH. The result of risk stratification indicates that patients with non-PAF, higher NT-proBNP, larger LAAV and LAV would have higher risks of AF recurrence. Conclusions:The proposed CNNSurv model has better performance than conventional statistical analysis, which may provide valuable guidance for clinical practice.

No abstract