Pulsed field ablation (PFA) is an emerging technology for the treatment of atrial fibrillation (AF), for which pre-clinical and early-stage clinical data are suggestive of some degree of preferentiality to myocardial tissue ablation without damage to adjacent structures. Here in the MANIFEST-17K study we assessed the safety of PFA by studying the post-approval use of this treatment modality. Of the 116 centers performing post-approval PFA with a pentaspline catheter, data were received from 106 centers (91.4% participation) regarding 17,642 patients undergoing PFA (mean age 64, 34.7% female, 57.8% paroxysmal AF and 35.2% persistent AF). No esophageal complications, pulmonary vein stenosis or persistent phrenic palsy was reported (transient palsy was reported in 0.06% of patients; 11 of 17,642). Major complications, reported for ~1% of patients (173 of 17,642), were pericardial tamponade (0.36%; 63 of 17,642) and vascular events (0.30%; 53 of 17,642). Stroke was rare (0.12%; 22 of 17,642) and death was even rarer (0.03%; 5 of 17,642). Unexpected complications of PFA were coronary arterial spasm in 0.14% of patients (25 of 17,642) and hemolysis-related acute renal failure necessitating hemodialysis in 0.03% of patients (5 of 17,642). Taken together, these data indicate that PFA demonstrates a favorable safety profile by avoiding much of the collateral damage seen with conventional thermal ablation. PFA has the potential to be transformative for the management of patients with AF.

Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications.