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 This study provides an update of survey-based data providing an overview of interventional electrophysiology over the last decade. Overall infrastructure, procedures, and training opportunities in Germany were assessed. Methods By analyzing mandatory quality reports, German cardiology centres performing electrophysiological studies were identified to repeat a questionnaire from 2010 and 2015. Results A complete questionnaire was returned by 192 centers performing about 75% of all ablations in Germany in 2020. In the presence of the COVID-19 pandemic, a total of 76.304 procedures including 68.407 ablations were reported representing a 38% increase compared to 2015. The median number of ablations increased from 180 in 2010 to 377 in 2020. AF was the most common arrhythmia ablated (51 vs. 35% in 2010). PVI with radiofrequency point-by-point ablation (64%) and cryo-balloon ablation (34%) were the preferred strategies. Less than 50 (75) PVI were performed by 31% (36%) of all centres. Only 25 and 24% of participating centres fulfilled EHRA and national requirements for training centre accreditation, respectively. There was a high number of EP centres with no fellows (38%). The proportion of female fellows in EP increased from 26% in 2010 to 33% in 2020. Conclusion Comparing 2020, 2010 and 2015, an increasing number of EP centres and procedures were registered. In 2020, more than every second ablation was for therapy of AF. In the presence of an increasing number of procedures, training opportunities were still limited, and most centres did not fulfill recommended EHRA or national requirements for accreditation. Graphical abstract
Aims The incidence of in-hospital post-interventional complications and mortality after ablation of supraventricular tachycardia (SVT) vary among the type of procedure and most likely the experience of the centre. As ablation therapy of SVT is progressively being established as first-line therapy, further assessment of post-procedural complication rates is crucial for health care quality. Methods and results We aimed at determining the incidence of in-hospital mortality and bleeding complications from SVT ablations in German high-volume electrophysiological centres between 2005 and 2020. All cases were registered by the German Diagnosis Related Groups—and the German Operation and Procedure Classification (OPS) system. A uniform search for SVT ablations from 2005 to 2020 with the same OPS codes defining the type of ablation/arrhythmia as well as the presence of a vascular complication, cardiac tamponade, and/or in-hospital death was performed. An overall of 47 610 ablations with 10 037 SVT ablations were registered from 2005 to 2020 among three high-volume centres. An overall complication rate of 0.5% (n = 38) was found [median age, 64; ±15 years; female n = 26 (68%)]. All-cause mortality was 0.02% (n = 2) and both patients had major prior co-morbidities precipitating a lethal outcome irrespective of the ablation procedure. Vascular complications occurred in 10 patients (0.1%), and cardiac tamponade was detected in 26 cases (0.3%). Conclusion The present case-based analysis shows an overall low incidence of in-hospital complications after SVT ablation highlighting the overall very good safety profile of SVT ablations in high-volume centres. Further prospective analysis is still warranted to guarantee continuous quality control and optimal patient care.
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.
The implantation of cardiac devices significantly reduces morbidity and mortality in patients with cardiac arrhythmias. Arrhythmias as well as therapy delivered by the device may impact quality of life of patients concerned considerably. Therefore we aimed at conducting a systematic search and meta-analysis of trials examining the impact of the implantation of cardiac devices, namely implantable cardioverter-defibrillators (ICD), pacemakers and left-ventricular assist devices (LVAD) on quality of life. After pre-registering the trial with the PROSPERO database, we searched Medline, PsycINFO, Web of Science and the Cochrane databases for relevant publications. Study quality was assessed by two independent reviewers using standardized protocols. A total of 37 trials met our inclusion criteria. Of these, 31 trials were cohort trials while 6 trials used a randomized controlled design. We found large pre-post effect sizes for positive associations between quality of life and all types of devices. The effect sizes for LVAD, pacemaker and ICD patients were g = 1.64, g = 1.32 and g = 0.64, respectively. There was a lack of trials examining the effect of implantation on quality of life relative to control conditions. Trials assessing quality of life in patients with cardiac devices are still scarce. Yet, the existing data suggest beneficial effects of cardiac devices on quality of life. We recommend that clinical trials on cardiac devices routinely assess quality of life or other parameters of psychological well-being as a decisive study endpoint. Furthermore, improvements in psychological well-being should influence decisions about implantations of cardiac devices and be part of patient education and may impact shared decision-making.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.