Risk stratification in Brugada syndrome through AI-enhanced electrocardiograms
Brugada syndrome (BrS) is an inherited electrical cardiac disorder that is associated with higher risks of ventricular fibrillation (VF) and sudden cardiac death (SCD) in patients without structural heart disease.
Three types of ECG patterns in the right precordial leads are recognized but only Type 1, a coved ST-segment elevation (> 2mm), occurring spontaneously or after a sodium-channel blocker provocation test, is considered diagnostic of the Brugada syndrome. Risk stratification is still challenging, especially in asymptomatic cases.
In general patients with documented ventricular fibrillation should receive an implantable cardioverter defibrillator to prevent sudden death against high rates of complications due to the device.
However, in asymptomatic people, the best approach is still unclear: a correct evaluation of the risk of developing an arrhythmic event could prevent premature deaths and unnecessary procedures. Because of the limitations of experimental research involving human cardiac tissue, alternative methods, such as computer modeling and deep learning-based artificial intelligence (AI), are of great interest.
The main idea of the research is that machine learning techniques can retrieve complex information from the entire electrocardiographic imaging, to overcome the problem of variability and bias of manually determined ECG markers, and correctly predict whether a patient will develop an arrhythmic event or not.
The project is subject to collaboration with a team of cardiologists from the Molinette Hospital in Turin coordinated by Dr. Giustetto C.
- PE7_7 Signal processing
- PE7_11 Components and systems for applications
- PE6_11 Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)
- LS7_14 Digital medicine, e-medicine, medical applications of artificial intelligence
- Machine learning
- Brugada syndrome
- Risk stratification