In a large cohort of patients, ESPM is a safe procedure that improves clinical symptoms in the majority of patients during long-term follow-up. We show for the first time that this also applies for cases where there is no DNPP but a characteristic ECG documentation, and vice versa.
This is the first collective analysis of a group of patients presenting with symptoms of pSVT and inducibility of only two AVNEBs. Procedural success and clinical long-term follow-up were in the range of the reported success rates of slow pathway modification of inducible AVNRT, independent of whether ECG documentation was present. Thus, SPM is a safe and effective therapy in patients with two AVNEBs.
Machine learning has immense novel but also disruptive potential for medicine. Numerous applications have already been suggested and evaluated concerning cardiovascular diseases. One important aspect is the detection and management of potentially thrombogenic arrhythmias such as atrial fibrillation. While atrial fibrillation is the most common arrhythmia with a lifetime risk of one in three persons and an increased risk of thromboembolic complications such as stroke, many atrial fibrillation episodes are asymptomatic and a first diagnosis is oftentimes only reached after an embolic event. Therefore, screening for atrial fibrillation represents an important part of clinical practice. Novel technologies such as machine learning have the potential to substantially improve patient care and clinical outcomes. Additionally, machine learning applications may aid cardiologists in the management of patients with already diagnosed atrial fibrillation, for example, by identifying patients at a high risk of recurrence after catheter ablation. We summarize the current state of evidence concerning machine learning and, in particular, artificial neural networks in the detection and management of atrial fibrillation and describe possible future areas of development as well as pitfalls.
Graphical abstract
Typical data flow in machine learning applications for atrial fibrillation detection.
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.
Introduction
Supraventricular tachycardias (SVT) are often difficult to document due to their intermittent, short-lasting nature. Smartphone-based one-lead ECG monitors (sECG) were initially developed for the diagnosis of atrial fibrillation. No data have been published regarding their potential role in differentiating inappropiate sinus tachycardia (IST) from regular SVT. If cardiologists could distinguish IST from SVT in sECG, economic health care burden might be significantly reduced.
Methods
We prospectively recruited 75 consecutive patients with known SVT undergoing an EP study. In all patients, four ECG were recorded: a sECG during SVT and during sinus tachycardia and respective 12-lead ECG. Two experienced electrophysiologists were blinded to the diagnoses and separately evaluated all ECG.
Results
Three hundred individual ECG were recorded in 75 patients (47 female, age 50 ± 18 years, BMI 26 ± 5 kg/m2, 60 AVNRT, 15 AVRT). The electrophysiologists’ blinded interpretation of sECG recordings showed a sensitivity of 89% and a specificity of 91% for the detection of SVT (interobserver agreement κ = 0.76). In high-quality sECG recordings (68%), sensitivity rose to 95% with a specificity of 92% (interobserver agreement of κ = 0.91). Specificity increased to 96% when both electrophysiologists agreed on the diagnosis. Respective 12-lead ECG had a sensitivity of 100% and specificity of 98% for the detection of SVT.
Conclusion
A smartphone-based one-lead ECG monitor allows for differentiation of SVT from IST in about 90% of cases. These results should encourage cardiologists to integrate wearables into clinical practice, possibly reducing time to definitive diagnosis of an arrhythmia and unnecessary EP procedures.
Graphical abstract
A smartphone-based one lead ECG device (panel A) can be used reliably to differentiate supraventricular tachycardia (panel B) from inappropriate sinus tachycardia when compared to a simultaneously conducted gold-standard electrophysiology study (panels C, D).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.