First clinical data on artificial intelligence-guided catheter ablation in long-standing persistent atrial...

Area of Science:

• Cardiology
• Medical Technology
• Artificial Intelligence in Medicine

Background:

• Persistent atrial fibrillation (AF) treatment remains challenging despite advanced ablation techniques.
• The underlying pathophysiology of persistent AF requires further understanding.
• This study investigates AI-guided ablation of spatiotemporal dispersions (DISPERS) for long-standing persistent AF.

Purpose of the Study:

• To analyze the outcomes and safety of catheter ablation targeting DISPERS identified by AI software.
• To evaluate the efficacy of DISPERS-guided ablation in patients with long-standing persistent AF.

Main Methods:

• Fifty consecutive patients with persistent AF underwent high-density mapping using the Volta VX1 AI software.
• Ablation included pulmonary vein isolation (PVI) and targeting of left and right atrial DISPERS.
• Follow-up involved regular clinic visits and 7-day Holter ECGs for 12 months.

Main Results:

• DISPERS ablation prolonged AF cycle length and terminated AF/atrial tachycardia (AT) in 24% of patients.
• No stroke or pericardial effusion occurred; two patients experienced major groin complications.
• After a blanking period, 52% experienced recurrence, primarily organized AT; 82% achieved stable sinus rhythm (SR) after an average of 1.46 procedures.

Conclusions:

• AI-guided DISPERS ablation, in addition to PVI, demonstrates high long-term success in eliminating AF and AT.
• Most recurrences were reentrant AT, and overall complication rates were low despite longer procedure times.
• Randomized studies are needed to confirm the long-term efficacy of AI-driven dispersion-guided ablation.