Unmasking concealed arrhythmia syndromes
Research type
Research Study
Full title
Unmasking concealed arrhythmia syndromes
IRAS ID
330619
Contact name
Zachary Whinnett
Contact email
Sponsor organisation
Research Governance and Integrity Team (RGIT) and Imperial College Healthcare NHS Trust
Duration of Study in the UK
3 years, 0 months, 1 days
Research summary
People with inherited heart rhythm disorders can die suddenly from dangerous heart rhythms. Whilst life-saving treatments are available, these heart abnormalities are very difficult to diagnose because the heart rhythm tracings (ECG) can appear completely normal when checked in hospital. In these individuals, their ECG may become abnormal during day-to-day activities, including exercise and sleep, allowing their condition to be detected.
First, we will develop a new way to detect these life-threatening inherited rhythm disorders, using artificial intelligence (AI). We will show a large number of example abnormal and normal ECGs to our AI computer program, which will teach itself to identify abnormal electrical signals. Next, we will demonstrate that the AI correctly identifies abnormal ECGs in patients with known inherited rhythm disorders, using prolonged recordings from an ambulatory ECG recording device. This will include Holter monitoring up to 12 leads, wearable cardiac monitoring devices and other ECG wearable technologies. We will investigate whether using AI, we can detect these abnormal electrical signals during their daily activities. Finally, we will use ultra-high-frequency ECGs to analyse subtle ECG signals that may be masked by conventional ECG, to look for markers of risk in patients with known arrhythmogenic conditions.
This research will be of significant benefit to patients with inherited arrhythmia syndromes and their relatives, who are at risk of sudden cardiac death. With greater diagnostic yields than conventional ambulatory ECG monitors, patients will be enabled to receive disease-targeted management sooner to potentially improve their prognosis. Being non-invasive, low risk and inexpensive, extended duration ambulatory ECG recordings obtained via smart textiles will likely form part of the staple clinical assessment in patients who present following an unexplained sudden cardiac arrest. Brugada detection ECG AI algorithms have several applications once validated, including in screening of affected relatives, high risk individuals and elite athletes.
REC name
North of Scotland Research Ethics Committee 1
REC reference
24/NS/0032
Date of REC Opinion
4 Apr 2024
REC opinion
Further Information Favourable Opinion