This study seeks to evaluate whether using non-invasive electrocardiograph (ECG) techniques, including long term ECG monitoring with wearable ECGs, can improve the detection of concealed Brugada syndrome.
Application of long term continuous ECG monitoring via ECG wearables and ambulatory ECG monitors to detect manifestations of Brugada syndrome. This approach will be combined with development of an AI (artificial intelligence) enabled ECG platform to automate Brugada ECG detection and analysis. The protocol will comprise the following parts: Study A: Brugada ECG AI development. This will automate the recognition of the type 1 Brugada ECG pattern on 12 lead ECGs. Study B: Remote arrhythmia diagnostics. A prospective observational study whereby recruited participants will be fitted with a wearable ECG or cardiac monitor to undergo continuous long term ambulatory ECG monitoring. The algorithms developed in study A will be applied to long term ECG data captured in this study. Study C: Arrhythmic risk stratification using ultra-high-frequency ECG. This exploratory study will look for markers of arrhythmic risk in patients with manifest and concealed arrhythmia syndromes.
Study Type
OBSERVATIONAL
Enrollment
200
12-lead ECG from a conventional ECG machine
Continuous long term ambulatory ECG monitoring using wearable ECG or cardiac monitor
Ultra-high-frequency ECG acquired using specific acquisition equipment
Imperial College Healthcare NHS Trust
London, United Kingdom
RECRUITINGSensitivity, specificity, and area under the curve (AUC) of AI algorithm for detection of Brugada type 1 ECG pattern on 12-lead ECGs.
Assessment of performance and accuracy of AI ECG detection algorithm for type 1 Brugada ECG.
Time frame: At completion of algorithm validation, approximately 12 months after study start
Detection rate of Brugada ECG pattern using extended-duration multi-electrode ambulatory ECG monitoring (wearable ECG) in patients with concealed Brugada syndrome.
AI ECG detection algorithm, developed in Study A, applied to full ECG recording to detect Type 1 Brugada ECG pattern.
Time frame: Up to 12 months from enrolment
Number of cases of Brugada or Long QT Syndrome (LQTS) detected using extended-duration multi-electrode ambulatory ECG monitoring in patients with idiopathic ventricular fibrillation (VF), after application of AI ECG detection algorithms.
AI ECG detection algorithms applied to full ECG recording to detect Type 1 Brugada ECG pattern or LQTS unmasking.
Time frame: Up to 12 months from enrolment
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.