Machine learning method for predicting pacemaker implantation following transcatheter aortic valve replacement.

BACKGROUND: An accurate assessment of permanent pacemaker implantation (PPI) risk following transcatheter aortic valve replacement (TAVR) is important for clinical decision making. The aims of this study were to investigate the significance and utility of pre- and post-TAVR ECG data and compare machine learning approaches with traditional logistic regression in predicting pacemaker risk following TAVR. METHODS: Five hundred fifity seven patients in sinus rhythm undergoing TAVR for severe aortic stenosis (AS) were included in the analysis. Baseline demographics, clinical, pre-TAVR ECG, post-TAVR data, post-TAVR ECGs (24 h following TAVR and before PPI), and echocardiographic data were recorded. A Random Forest (RF) algorithm and logistic regression were used to train models for assessing the likelihood of PPI following TAVR. RESULTS: Average age was 80 ± 9 years, with 52% male. PPI after TAVR occurred in 95 patients (17.1%). The optimal cutoff of delta PR (difference between post and pre TAVR PR intervals) to predict PPI was 20 ms with a sensitivity of 0.82, a specificity of 0.66. With regard to delta QRS, the optimal cutoff was 13 ms with a sensitivity of 0.68 and a specificity of 0.59. The RF model that incorporated post-TAVR ECG data (AUC 0.81) more accurately predicted PPI risk compared to the RF model without post-TAVR ECG data (AUC 0.72). Moreover, the RF model performed better than logistic regression model in predicting PPI risk (AUC: 0.81 vs. 0.69). CONCLUSIONS: Machine learning using RF methodology is significantly more powerful than traditional logistic regression in predicting PPI risk following TAVR.

Heart rate-corrected QT interval in men increases during winter months.

BACKGROUND: Sudden cardiac death increases during winter months in both men and women. The heart rate-corrected QT (QTc) interval exhibits circadian variation. However, little is known about QTc interval variation with month of year. OBJECTIVE: We sought to determine whether the QTc interval varies with month of year. METHODS: We retrospectively analyzed a database of 24,370 electrocardiograms (ECGs) to determine seasonal variation in QTc intervals. The analysis data set included 7,976 baseline ECGs, one each for 3,700 men and 4,276 women. ECGs selected for analysis were normal, recorded in regions north of the equator, and taken on subjects >or=18 years old. The QT correction for heart rate (HR) was performed using QTc = QT*(HR/60)(0.4). The monthly mean QTc intervals were compared, for men and women separately, using a one-way analysis of variance with the Bonferroni correction for multiple comparisons. RESULTS: Subject ages ranged from 18 to 95 years. The monthly mean QTc intervals were consistently greater for women than for men by 5.2 +/- 2.3 ms. After correction for multiple comparisons, the difference between the greatest and least monthly mean QTc interval was 6.1 +/- 1.5 ms (P <.01) for men and 3.5 ms (nonsignificant) for women. The maximum monthly mean QTc interval of 413 +/- 18 ms (n = 560; P <.05) occurred in October for men and of 417 +/- 16 ms (n = 350) in March for women, but it was not significant. CONCLUSIONS: Significant seasonal variation in QTc interval exists among male subjects >or=18 years of age with normal baseline ECGs, with the QTc interval being longest in October. No significant variation was seen for women.

Mortality as an endpoint in atrial fibrillation.

The aim of this study was to evaluate the use of mortality as an appropriate endpoint in studies of atrial fibrillation. Almost none of the atrial fibrillation trials has shown a significant difference in mortality among the various treatment arms because the studies are small, and many patient-years are required to show significant differences. Differences can be found when mortality is used as part of a combined endpoint and in meta-analyses of atrial fibrillation trials. Some trials of atrial fibrillation in the setting of conditions predisposing to high mortality, such as heart failure, postmyocardial infarction, and perioperative state for surgical procedures, can have mortality differences. Nevertheless, mortality has a role in validating the safety of new therapies and can be used as a measure of the impact and prognostic significance of atrial fibrillation in various disease settings.