Introduction: The Long-QT Syndrome (LQTS) is the most common ion channelopathy typically presenting with a prolonged QT-interval and triggered clinical symptoms like syncope or sudden cardiac death. Patients may present with a concealed phenotype making the diagnosis challenging. Correctly diagnosing high-risk patients is pivotal to start early preventive treatment.

Objective: Identification of congenital and often concealed LQTS by utilizing novel deep learning network architectures, which are specifically designed for multi-channel time series and therefore particularly suitable for ECG data. 

Design and Results: A retrospective artificial intelligence (AI)-based analysis was performed using 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 QT_c parameters.

Conclusion: In this study, the XceptionTime model outperformed the FCN model for LQTS patients with even better results than prior studies, even when used a common patient cohort with cardiovascular co-morbidities. AI-based ECG analysis is a promising step for correct LQTS patient identification, especially if common diagnostic measures might be misleading.