Maor, Elad

Abstract Background Mitral regurgitation (MR) and tricuspid regurgitation (TR) are prevalent valvular heart diseases associated with significant morbidity and mortality. Traditional echocardiography faces limitations in availability, cost, consistency, and reliability, leading to misdiagnosis and undertreatment. The application of artificial intelligence (AI) to echocardiographic scans has the potential to address these challenges. Methods This study evaluates the performance of an AI algorithm on an external population. The algorithm utilizes deep learning networks to analyze echocardiographic exams for diagnosing atrioventricular valve disorders. We tested the algorithm on transthoracic echocardiography data collected from a single center between 2013 and 2023. The model's performance was compared to ground truth values using two classification schemes: distinguishing between normal-mild and moderate-severe regurgitation, and categorizing results into four groups: normal, mild, moderate, and severe. Results The MR cohort included 280 patients, while the TR cohort comprised 298 patients. The model demonstrated a robust ability to identify clinically significant (moderate and above) atrioventricular valve regurgitation. The MR model achieved an area under the curve (AUC) of 0.98 (95% CI: 0.97–0.99), with 91% accuracy, 95% sensitivity, and 89% specificity. In comparison, the TR model exhibited an AUC of 0.96 (95% CI: 0.94–0.98), with 84% accuracy, 91% sensitivity, and 80% specificity. Conclusion The model demonstrated high diagnostic accuracy and reliability in assessing atrioventricular valve regurgitation severity, highlighting its potential as a valuable clinical tool. The findings underscore the role of AI in complementing expert evaluations and improving access to effective diagnostics, with future applications potentially including point-of-care diagnosis and monitoring of disease progression.

Abstract Background Many patients with atrial fibrillation (AF) suffer life-limiting symptoms and heart failure. Although enormous advances in rhythm control have been made, device-based therapies for treating recurrent episodes are limited. Using pulsed electric fields (PEF) to induce reversible electroporation of cardiac tissue may effectively terminate AF. Purpose To assess the feasibility of PEF delivery for converting atrial arrhythmias via reversible electroporation. Methods Four swine models were used in this acute study. Custom-made decapolar catheters for PEF delivery were deployed with the following configurations: 1. Endocardial right atrium (RA) and coronary sinus (CS), n=2; 2. Endocardial RA and epicardial left atrium (epiLA), n=2. AF and atrial flutter (AFL) were induced with programmed stimulation. PEF delivery was performed using the BTX 830 generator. For each attempt, a single monophasic pulse at 10 or 20µs pulse width was administered, with voltage varied across attempts (range 750-3000V). Successful (type 1 and 2 breaks) and unsuccessful conversion attempts were recorded. Post-PEF signal changes and arrhythmias were identified. Results A total of 58 AF/AFL (28 and 30 respectively) episodes were induced. Of the 37 successful conversion attempts, 33 (89.1%) were type 1 breaks. Conversion success probabilities generally increased with higher voltages for both configurations. >70% conversion success was seen with ≥1500V for the RA/CS configuration and ≥2000V for the RA/epiLA configuration. Arrhythmias including intra-atrial delay and high-grade atrioventricular block were seen, usually following successive PEF deliveries. Significant muscle stimulation was provoked with the current experimental setup. Conclusion Termination of atrial arrhythmias with PEF delivery is feasible, although further work is required to optimize its efficacy and safety.

Abstract Background Ventricular fibrillation (VF) is a leading cause of sudden cardiac death worldwide. Defibrillation via direct current shocks is effective but associated with significant pain and morbidity, prompting the need for alternative approaches. Reversible electroporation of cardiac tissue with pulsed electric fields (PEF) may be an effective means of terminating VF. Purpose To assess the feasibility of PEF delivery for terminating VF. Methods 5 acute swine models were used. Mechanical circulatory support with peripheral veno-arterial extracorporeal membrane oxygenation +/- percutaneous left ventricular assist device (Impella 5.5 L) was implemented and titrated to a mean arterial pressure ≥65 mmHg. Decapolar catheters were introduced into the endocardial right and/or left ventricle as well as epicardium. VF was induced with R on T shocks or rapid ventricular pacing. PEF was delivered with the endocardial catheter as the cathode and epicardial catheter as the anode; monophasic pulses (5-10) at 3000V, 100µs, and 200ms inter-pulse intervals were used. If VF persisted post-PEF, catheters were repositioned into regions of intact voltages for repeat delivery. Results 10 VF episodes were induced, 7 of which were successfully terminated with PEF delivery (70.0%). The median number of attempts to achieve VF termination was 2 (range 1-5). The post-VF rhythm was complete heart block with ventricular asystole in all successful defibrillation attempts, with no recovery after 30 minutes of observation. Significant muscle stimulation was seen with the utilized PEF parameters and catheter configurations. Conclusion Termination of VF using PEF – pulsed field defibrillation – is possible. However, further study is required to optimize delivery parameters/configurations to improve effectiveness and avoid muscle stimulation as well as conduction abnormalities.