ABSTRACT
Introduction Catheter ablation (CA) of atrial fibrillation (AF) represents a mainstay in the treatment of this increasingly prevalent arrhythmia. Prospective clinical trials investigating the efficacy of CA may poorly represent real-world patient populations. However, many real-world clinical datasets possess missing data, which may impede their applicability in research. Thus, we sought to use ensemble modeling to address missing data and develop a model to estimate the probability of AF recurrence following CA. Methods We retrospectively analyzed clinical variables in 476 patients who underwent an initial CA of AF. Univariate and multivariate logistic regression was performed to determine those variables predictive of AF recurrence. A multivariate logistic model was created to estimate the probability of AF recurrence after CA. Missing data were addressed using ensemble modeling, and variable selection was performed using the aggregate of multiple models. Results After analysis, six variables remained in the model: AF during the post-procedural blanking period, coexistence of atrial flutter, end-stage renal disease, reduced left ventricular ejection fraction, prior failure of anti-arrhythmic drugs, and valvular heart disease. Predictive modeling was performed using these variables for 1000 randomly partitioned datasets (80% training, 20% testing) and 1000 random imputations for each partitioned dataset. The model predicted AF recurrence with an accuracy of 74.34 ± 3.99% (recall: 54.03 ± 8.15%; precision: 89.30 ± 4.21%; F1 score: 81.08 ± 3.65%). Conclusion We successfully identified six clinical variables that, when modeled, predicted AF recurrence following CA with a high degree of classification accuracy. Application of this model to patients undergoing CA of AF may help identify those at risk of post-procedural AF recurrence.
ABSTRACT
PURPOSE: We sought to explore the association between the spinal cord injury (SCI) level on the cardiac structure and the function observed in elite para-cyclists. METHODS: Cross-sectional echocardiographic data from 44 elite SCI hand cyclists (39.8 ± 9 yr, 68% male/32% female) stratified by the level of SCI (cervical, N = 9; T1-T5, N = 10; below T5, N = 25) and 19 non-SCI blind/visually impaired (BVI) tandem cyclists (32.4 ± 7 yr, 58% male/42% female) were analyzed before the initiation of international competition. RESULTS: Compared with non-SCI BVI cyclists, cervical SCI para-cyclists were observed with lower indexed left ventricular (LV) mass (99.6 ± 12 vs 125 ± 20 g·m, P = 0.01), posterior wall thickness (4.5 ± 0.3 vs 5.8 ± 0.7 mm·m, P < 0.001), interventricular septal wall thickness (4.8 ± 0.5 vs 5.7 ± 0.7 mm·m; P = 0.03), and left atrial volume (21 ± 3.5 vs 28 ± 7 mL·m; P = 0.02). In multivariable analyses, cervical SCI was independently associated with decreased LV wall thickness [interventricular septum (ß = -0.67, P = 0.01), posterior wall (ß = -0.98, P = 0.001)], decreased LV mass (ß = -21, P < 0.001), and decreased left atrial volume index (ß = -6.9, P = 0.001) compared with other levels of SCI and non-SCI BVI cyclists. There were no differences in ventricular function among any of the athlete groups. CONCLUSION: Compared with para-cyclists with lower levels of SCI, the athletes with cervical SCI demonstrate attenuated cardiac size and concentric LV hypertrophy.