Validation of a machine learning algorithm to identify pulmonary vein isolation during ablation procedures for the treatment of atrial fibrillation: results of the PVISION study.

AIMS: Pulmonary vein isolation (PVI) is the cornerstone of ablation for atrial fibrillation. Confirmation of PVI can be challenging due to the presence of far-field electrograms (EGMs) and sometimes requires additional pacing manoeuvres or mapping. This prospective multicentre study assessed the agreement between a previously trained automated algorithm designed to determine vein isolation status with expert opinion in a real-world clinical setting. METHODS AND RESULTS: Consecutive patients scheduled for PVI were recruited at four centres. The ECGenius electrophysiology (EP) recording system (CathVision ApS, Copenhagen, Denmark) was connected in parallel with the existing system in the laboratory. Electrograms from a circular mapping catheter were annotated during sinus rhythm at baseline pre-ablation, time of isolation, and post-ablation. The ground truth for isolation status was based on operator opinion. The algorithm was applied to the collected PV signals off-line and compared with expert opinion. The primary endpoint was a sensitivity and specificity exceeding 80%. Overall, 498 EGMs (248 at baseline and 250 at PVI) with 5473 individual PV beats from 89 patients (32 females, 62 ± 12 years) were analysed. The algorithm performance reached an area under the curve (AUC) of 92% and met the primary study endpoint with a sensitivity and specificity of 86 and 87%, respectively (P = 0.005; P = 0.004). The algorithm had an accuracy rate of 87% in classifying the time of isolation. CONCLUSION: This study validated an automated algorithm using machine learning to assess the isolation status of pulmonary veins in patients undergoing PVI with different ablation modalities. The algorithm reached an AUC of 92%, with both sensitivity and specificity exceeding the primary study endpoints.

Long-term prognosis of patients with life-threatening ventricular arrhythmias induced by coronary artery spasm.

Aims: Coronary artery spasm (CAS) is associated with ventricular arrhythmias (VA). Much controversy remains regarding the best therapeutic interventions for this specific patient subset. We aimed to evaluate the clinical outcomes of patients with a history of life-threatening VA due to CAS with various medical interventions, as well as the need for ICD placement in the setting of optimal medical therapy. Methods and results: A multicentre European retrospective survey of patients with VA in the setting of CAS was aggregated and relevant clinical and demographic data was analysed. Forty-nine appropriate patients were identified: 43 (87.8%) presented with VF and 6 (12.2%) with rapid VT. ICD implantation was performed in 44 (89.8%). During follow-up [59 (17-117) months], appropriate ICD shocks were documented in 12. In 8/12 (66.6%) no more ICD therapies were recorded after optimizing calcium channel blocker (CCB) therapy. SCD occurred in one patient without ICD. Treatment with beta-blockers was predictive of appropriate device discharge. Conversely, non-dihydropyridine CCB therapy was significantly protective against VAs. Conclusion: Patients with life-threatening VAs secondary to CAS are at particularly high-risk for recurrence, especially when insufficient medical therapy is administered. Non-dihydropyridine CCBs are capable of suppressing episodes, whereas beta-blocker treatment is predictive of VAs. Ultimately, in spite of medical intervention, some patients exhibited arrhythmogenic events in the long-term, suggesting that ICD implantation may still be indicated for all.