ABSTRACTBackgroundArtificial intelligence (AI)‐enhanced electrocardiography (ECG) has been developed to detect paroxysmal atrial fibrillation (AF) from sinus rhythm ECGs (SR‐ECGs). For broader applicability, model development across institutions and ECG systems is essential.MethodsWe developed an AI‐enhanced ECG model using SR‐ECGs from Tokai University (n = 172,613; Nihon Kohden [NK] system) and The Cardiovascular Institute (n = 19,170; GE MUSE system). AF‐labeled SR‐ECGs were defined as recordings within 31 days of an AF episode, while SR‐labeled SR‐ECGs were those with ≥ 1095 days of AF‐free follow‐up. Three datasets were constructed: Dataset 1 (Tokai University, all departments, NK), Dataset 2 (Tokai University, Cardiology Department, NK), and Dataset 3 (The Cardiovascular Institute, Cardiology Department, MUSE). We developed five models: scratch models (S1–S3) trained on Datasets 1–3, and fine‐tuned models (F1, F2) trained on Datasets 1 and 2 after pretraining on Dataset 3. Models were evaluated using A1–A3 (same as Datasets 1–3) and B1–B3, which differed in ECG resolution and compression (B1: original MUSE, B2: MUSE‐NK intermediate, B3: NK‐converted).ResultsModel F2, fine‐tuned on homogeneous datasets from cardiology departments, showed consistently high performance (AUC: A1 = 0.885, A2 = 0.829, A3 = 0.845). Model F1, fine‐tuned on heterogeneous datasets, demonstrated lower performance (AUC: A1 = 0.837, A2 = 0.726, A3 = 0.660). Model performance was consistent across different ECG format variants (B1–B3).ConclusionFine‐tuning on homogeneous data improved performance and generalizability, whereas heterogeneous data led to reduced performance. ECG system format differences had minimal impact on model accuracy.

ABSTRACTBackgroundRheumatic heart disease (RHD) remains a significant health burden, particularly in low‐ and middle‐income countries, with rheumatic mitral stenosis (MS) contributing substantially to cardiovascular morbidity and mortality. Percutaneous transvenous mitral commissurotomy (PTMC) is an effective treatment for symptomatic MS, yet its long‐term impact on atrial electromechanical properties remains underexplored.MethodsWe conducted a prospective observational study involving 53 patients (mean age 33.3 ± 6.44 years) who underwent successful PTMC for severe MS. Patients were followed up for a mean duration of 5.34 ± 0.55 years post‐procedure. Atrial electromechanical parameters, including P‐wave dispersion (PWD) and atrial electromechanical delay (AEMD), were assessed using electrocardiography and tissue Doppler echocardiography at baseline, 1 year, 3 years, and 5 years post‐PTMC.ResultsPTMC resulted in significant improvements in mitral valve area and gradients immediately post‐procedure, which were sustained over the long term. AEMD showed statistically significant improvement at mean 3 years and 5.3 years post‐PTMC, indicating enhanced electromechanical function. Conversely, PWD demonstrated gradual and significant improvement at intermediate follow‐up, with stabilization after 3 years. Patients who developed atrial fibrillation (AF) or restenosis during follow‐up exhibited higher baseline values, suggesting a potential predictive role for these parameters.ConclusionOur study demonstrates that PTMC leads to sustained improvements in atrial electromechanical function indices over long‐term follow‐up. AEMD and PWD serve as valuable markers for assessing atrial remodeling post‐PTMC, with implications for predicting AF and restenosis risk in patients with rheumatic MS.

ABSTRACTBackgroundLeft bundle branch area pacing (LBBAP) is an emerging physiological pacing technique that restores ventricular electrical synchrony by directly engaging the left conduction system. It has been proposed as an alternative to conventional pacing strategies, particularly in heart failure patients with reduced left ventricular ejection fraction (LVEF ≤ 50%).MethodsA systematic literature search of PubMed, MEDLINE, and Scopus was conducted up to December 2024 in accordance with PRISMA guidelines. Sixteen studies involving 5680 patients were included. Reported outcomes included changes in LVEF, QRS duration (QRSd), hospitalization rates, complications, and mortality. Due to heterogeneity among studies, a qualitative narrative synthesis was performed.ResultsLBBAP was associated with significant improvements in cardiac function, with most studies reporting increased LVEF and marked reductions in QRSd, indicating improved electrical synchrony. Complication rates were low, with rare events such as pneumothorax and lead dislodgement. Heart failure–related hospitalizations were lower with LBBAP compared with biventricular pacing (19.05% vs. 30.00%), while mortality rates remained low across pacing strategies. Overall, LBBAP demonstrated superior electrical resynchronization and favorable clinical outcomes compared with conventional pacing modalities.ConclusionLBBAP is a promising pacing strategy that improves electrical synchrony and cardiac function with a favorable short‐ to mid‐term safety profile. Further large‐scale randomized studies are needed to establish its long‐term efficacy and safety.

ABSTRACTTemporary pacing during acute inferior MI or no‐reflow can trigger ventricular fibrillation rather than prevent it. Four mechanisms are highlighted: (1) acute ischemia lowers VF threshold and creates repolarization heterogeneity; (2) fragmented electrograms cause undersensing and asynchronous spikes; (3) bradycardia‐related long RR cycles position spikes on the T‐wave (“R‐on‐T”); and (4) catheter micro‐displacement induces mechanical extrasystoles. We propose a bedside decision framework—three questions before pacing—and a prevention bundle focused on urgent ischemia reversal, continuous electrogram surveillance, and early electrode removal. Bradycardia in this setting is often transient, but the electrophysiological vulnerability is not. Treating ischemia first and avoiding unnecessary pacing are paramount to prevent iatrogenic arrhythmia.