RESUMEN
Artificial Intelligence (AI) applications and Machine Learning (ML) methods have gained much attention in recent years for their ability to automatically detect patterns in data without being explicitly taught rules. Specific features characterise the ECGs of patients with Brugada Syndrome (BrS); however, there is still ambiguity regarding the correct diagnosis of BrS and its differentiation from other pathologies. This work presents an application of Echo State Networks (ESN) in the Recurrent Neural Networks (RNN) class for diagnosing BrS from the ECG time series. 12-lead ECGs were obtained from patients with a definite clinical diagnosis of spontaneous BrS Type 1 pattern (Group A), patients who underwent provocative pharmacological testing to induce BrS type 1 pattern, which resulted in positive (Group B) or negative (Group C), and control subjects (Group D). One extracted beat in the V2 lead was used as input, and the dataset was used to train and evaluate the ESN model using a double cross-validation approach. ESN performance was compared with that of 4 cardiologists trained in electrophysiology. The model performance was assessed in the dataset, with a correct global diagnosis observed in 91.5 % of cases compared to clinicians (88.0 %). High specificity (94.5 %), sensitivity (87.0 %) and AUC (94.7 %) for BrS recognition by ESN were observed in Groups A + B vs. C + D. Our results show that this ML model can discriminate Type 1 BrS ECGs with high accuracy comparable to expert clinicians. Future availability of larger datasets may improve the model performance and increase the potential of the ESN as a clinical support system tool for daily clinical practice.
RESUMEN
BACKGROUND: Mitral isthmus (MI) conduction block is a fundamental step in anatomical approach treatment for persistent atrial fibrillation (PeAF). However, MI block is hardly achievable with endocardial ablation only. Retrograde ethanol infusion (EI) into the vein of Marshall (VOM) facilitates MI block. Fluorographic myocardial staining (MS) during VOM-EI could be helpful in predicting procedural alcoholization outcome even if its role is qualitatively assessed in the routine. The aim was to quantitatively assess MS during VOM-EI and to evaluate its association with MI block achievement. METHODS: Consecutive patients undergoing catheter ablation for PeAF at Fondazione Toscana Gabriele Monasterio (Pisa, Italy) from February 2022 to May 2023 were considered. Patients with identifiable VOM were included. A proposed index of MS (MSI) was retrospectively calculated in each included patient. Correlation of MSI with low-voltage zones (LVZ) extension after VOM-EI and its association with MI block achievement were assessed. RESULTS: In total, 42 patients out of 49 (85.8%) had an identifiable VOM. MI block was successfully achieved in 35 patients out of 42 (83.3%). MSI was significantly associated with the occurrence of MI block (OR 1.24 (1.03-1.48); p = 0.022). A higher MSI resulted in reduced ablation time (p = 0.014) and reduced radiofrequency applications (p = 0.002) to obtain MI block. MSI was also associated with MI block obtained by endocardial ablation only (OR 1.07 (1.02-1.13); p = 0.002). MSI was highly correlated with newly formed LVZ extension (r = 0.776; p = 0.001). CONCLUSIONS: In our study cohort, optimal MSI predicts MI block and facilitates its achievement with endocardial ablation only.