Catheter ablation outcome prediction in persistent atrial fibrillation using weighted principal component analysis

► Atrial signal spatial spatio-temporal orgarnization measures are exploited for catheter ablation outcome in persistent AF. ► These measures are determined by WPCA, for the first time applied to ECG processing for AF analysis. ► WPCA allows the exploitation of ECG multivariate properties and the enhancement of the most descriptive leads. ► Classification performance of our multilead descriptor outperforms that of classical single-lead predictors. ► It proves to be more robust to lead selection as well.