Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm.

AIMS: Guidelines recommend opportunistic screening for atrial fibrillation (AF), using a 30 s single-lead electrocardiogram (ECG) recorded by a wearable device. Since many patients have paroxysmal AF, identification of patients at high risk presenting with sinus rhythm (SR) may increase the yield of subsequent long-term cardiac monitoring. The aim is to evaluate an AI-algorithm trained on 10 s single-lead ECG with or without risk factors to predict AF. METHODS AND RESULTS: This retrospective study used 13 479 ECGs from AF patients in SR around the time of diagnosis and 53 916 age- and sex-matched control ECGs, augmented with 17 risk factors extracted from electronic health records. AI models were trained and compared using 1- or 12-lead ECGs, with or without risk factors. Model bias was evaluated by age- and sex-stratification of results. Random forest models identified the most relevant risk factors. The single-lead model achieved an area under the curve of 0.74, which increased to 0.76 by adding six risk factors (95% confidence interval: 0.74-0.79). This model matched the performance of a 12-lead model. Results are stable for both sexes, over ages ranging from 40 to 90 years. Out of 17 clinical variables, 6 were sufficient for optimal accuracy of the model: hypertension, heart failure, valvular disease, history of myocardial infarction, age, and sex. CONCLUSION: An AI model using a single-lead SR ECG and six risk factors can identify patients with concurrent AF with similar accuracy as a 12-lead ECG-AI model. An age- and sex-matched data set leads to an unbiased model with consistent predictions across age groups.

Initial experience of left bundle branch area pacing using stylet-driven pacing leads: A multicenter study.

BACKGROUND: Left bundle branch area pacing (LBBAP) has been performed exclusively using lumen-less pacing leads (LLL) with fixed helix design. This registry study explores the safety and feasibility of LBBAP using stylet-driven leads (SDL) with extendable helix design in a multicenter patient population. METHODS: This study prospectively enrolled consecutive patients who underwent LBBAP for bradycardia pacing or heart failure indications at eight Belgian hospitals. LBBAP was attempted using SDL (Solia S60; Biotronik) delivered through dedicated delivery sheath (Selectra3D). Implant success, complications, procedural, and pacing characteristics were recorded at implant and follow-up. RESULTS: The study enrolled 353 patients (mean age 76 ± 39 years, 43% female). The mean number of implants per center was 25 (range: 5-162). Overall, LBBAP with SDL was successful in 334/353 (94%), varying from 93% to 100% among centers. Pacing response was labeled as left bundle branch pacing in 73%, whereas 27% were labeled as myocardial capture. Mean paced QRS duration and stimulus to left ventricular activation time measured 126 ± 21 ms and 74 ± 17. SDL-LBBAP resulted in low pacing thresholds (0.6 ± 0.4 V at 0.4 ms), which remained stable at 12 months follow-up (0.7 ± 0.3, p = .291). Lead revisions for SDL-LBBAP occurred in 5 (1.4%) patients occurred during a mean follow up of 9 ± 5 months. Five (1.4%) septal coronary artery fistulas and 8 (2%) septal perforations occurred, none of them causing persistent ventricular septal defects. CONCLUSION: The use of SDL to achieve LBBAP is safe and feasible, characterized by high implant success in low and high volume centers, low complication rates, and stable low pacing thresholds.

Symptomatic arrhythmogenic right ventricular dysplasia/cardiomyopathy. A two-centre retrospective study of 15 symptomatic ARVD/C cases and focus on the diagnostic value of MRI in symptomatic ARVD/C patients.

BACKGROUND: Arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C) is associated with sudden death in the young and heart failure in the elderly. The purpose is to review 15 symptomatic ARVD/C cases and also to describe the use of MRI as a diagnostic tool. METHODS AND RESULTS: This retrospective analysis includes 15 patients who presented with symptomatic ARVD/C. Diagnosis was made upon the criteria proposed by the European Society of Cardiology. In all patients there was at least 1 or more abnormal MRI sign. The most frequent abnormalities were focal right ventricular dyskinesia (64%), MRI fatty infiltration (57%) and right ventricular aneurysm or right ventricular outflow tract microaneurysms (57%). Presenting symptoms were palpitations (60%), atypical chest pain (46%), syncope (40%), and aborted sudden death (26%). T-inversion in V2-V3 was seen in 60% of the patients. Thirteen patients (86%) received an ICD implantation. The mean follow-up per patient was 89 months, which resulted in a total follow-up of 111 patient years. Forty-six percent of the patients with an ICD had one or more appropriate shocks during follow-up. To this date no mortality was reported. CONCLUSION: This retrospective study demonstrates that symptomatic ARVD/C patients typically present with symptoms of syncope, palpitations in association with ventricular tachycardia and in a quarter of the cases with aborted sudden cardiac death. The electrocardiogram mostly shows T inversion in the anterior leads. All patients were treated with medication and ICD-implantation or VT-ablation. The malignant nature of the disease in symptomatic ARVD/C patients is stressed by the fact that the presenting symptom is aborted sudden death in a quarter of the cases and the fact that nearly half of the patients with an ICD had at least one appropriate shock during follow-up. There was an abnormal MRI in 100% of the investigated patients. In 20% (3 patients), the MRI criterion (right ventricular dilatation/bulging/aneurysm) was necessary to meet the ESC criteria. Therefore it has become an important tool in our diagnostic work-up when ARVD/C is suspected. We also suggest a change in the diagnostic criteria of ARVD/C. Whereas fatty infiltration seen on RV biopsy is a major criterion, MRI fatty infiltration is not regarded as a diagnostic criterion by the task force to this day.

Amiodarone and polymorphic ventricular tachycardia: to slow down or to accelerate the underlying rhythm?

Polymorphic ventricular tachycardia (VT) comprises a variety of different subforms. Two patients were admitted to our hospital and developed polymorphic VT under treatment with amiodarone. However, each of them turned out to have a very different form of the arrhythmia and therefore required a different therapeutic approach. The clinical decision-making required a distinction between the two forms, and the following therapeutic approach included terminating the administration of amiodarone in the first case and continuing administration in the other case. As the most common forms of polymorphic VT are described, it becomes clear that each different form should be identified because of the important therapeutic implications. In particular, the role of amiodarone can be quite different in the management of these different forms of polymorphic VT.