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.

Moderate Aortic Stenosis in Patients With Heart Failure.

BACKGROUND AND OBJECTIVES: Moderate aortic stenosis (AS) confers a surprisingly adverse prognosis, approaching that of severe AS. The objective of this study was to describe the clinical course of patients with moderate AS with evidence of concomitant heart failure manifesting as elevated brain natriuretic peptide (BNP) levels. METHODS: This is a single-center, retrospective cohort study of 332 patients with elevated BNP. 165 patients with moderate AS were compared with 167 controls with none-mild AS. The Median follow-up duration was 3.85 years. The primary outcome was a composite endpoint of all-cause hospitalizations and all-cause mortality. RESULTS: BNP levels were 530 and 515 pg/mL in the study and the control groups, respectively. Moderate AS had significantly higher rates of primary composite endpoint in both univariate analysis (hazard ratio [HR], 1.50; 95% confidence interval [CI], 1.14-1.97; p=0.004) and adjusted analysis (HR, 1.45; 95% CI, 1.05-2.01; p=0.02). Moderate AS had 1.41 (95% CI, 1.18-1.69; p<0.001) times more all-cause hospitalization per patient-year of follow-up compared to controls in the univariate model. After adjustment for significant covariates, moderate AS remained an independent predictor of all-cause hospitalizations (incidence rate ratio [IRR], 1.45; 95% CI, 1.18-1.79; p=0.005). Furthermore, moderate AS was significantly associated with higher all-cause hospitalization rates in both heart failure with reduced ejection fraction (IRR, 1.33; 95% CI, 1.02-1.75; p=0.038) and heart failure with preserved ejection fraction [IRR], 1.31; 95% CI, 1.03-1.67; p=0.026). CONCLUSIONS: Moderate AS in conjunction with elevated BNP portends a significantly worse prognosis than those without moderate AS and should be followed closely.