RESUMO
INTRODUCTION: The long-QT syndrome (LQTS) is the most common ion channelopathy, typically presenting with a prolonged QT interval and clinical symptoms such as syncope or sudden cardiac death. Patients may present with a concealed phenotype making the diagnosis challenging. Correctly diagnosing at-risk patients is pivotal to starting early preventive treatment. OBJECTIVE: Identification of congenital and often concealed LQTS by utilizing novel deep learning network architectures, which are specifically designed for multichannel time series and therefore particularly suitable for ECG data. DESIGN AND RESULTS: A retrospective artificial intelligence (AI)-based analysis was performed using a 12-lead ECG of genetically confirmed LQTS (n = 124), including 41 patients with a concealed LQTS (33%), and validated against a control cohort (n = 161 of patients) without known LQTS or without QT-prolonging drug treatment but any other cardiovascular disease. The performance of a fully convolutional network (FCN) used in prior studies was compared with a different, novel convolutional neural network model (XceptionTime). We found that the XceptionTime model was able to achieve a higher balanced accuracy score (91.8%) than the associated FCN metric (83.6%), indicating improved prediction possibilities of novel AI architectures. The predictive accuracy prevailed independently of age and QTc parameters. CONCLUSIONS: In this study, the XceptionTime model outperformed the FCN model for LQTS patients with even better results than in prior studies. Even when a patient cohort with cardiovascular comorbidities is used. AI-based ECG analysis is a promising step for correct LQTS patient identification, especially if common diagnostic measures might be misleading.
RESUMO
BACKGROUND: The first-line therapy for atrioventricular nodal reentry tachycardia (AVNRT) is catheter-based slow pathway modulation. If AVNRT is not inducible during an electrophysiological study, an empirical slow pathway modulation (ESPM) may be considered in patients with dual atrioventricular nodal physiology and/or a typical electrocardiogram (ECG). METHODS: We screened 149 symptomatic patients who underwent ESPM in our department between 1993 and 2013. All patients fulfilled the following criteria: (1) either dual atrioventricular nodal (AVN) physiology with up to 2 AVN echo beats or characteristic ECG documentation or both, (2) noninducibility of AVNRT by programmed stimulation, and (3) completion of a telephone questionnaire for long-term follow-up. Out of this population we retrospectively investigated 13 patients who were primarily noninducible but in whom an AVNRT occurred during or after radiofrequency (RF) delivery. RESULTS: When AVNRT occurred, the procedure lost its empirical character, and RF delivery was continued until the procedural endpoint of noninducibility of AVNRT. This endpoint was reached in all but one patient (92%). After a follow-up of 73 ± 15 months, this patient was the only one who reported no benefit from the procedure. CONCLUSIONS: Out of 149 initially noninducible patients, a considerable number (9%) exhibited AVNRT during or after RF delivery. These patients crossed over from empirical to controlled slow pathway modulation resulting in a good clinical outcome. Our observations should encourage electrophysiologists to repeat programmed stimulation even after initial empirical RF delivery to retest for inducibility.