A Deep Learning–Enabled Electrocardiogram Model for the Identification of a Rare Inherited Arrhythmia: Brugada Syndrome
Problem
Brugada syndrome is a rare inherited arrhythmia and a major cause of sudden cardiac death in young people, requiring early identification of its type 1 ECG pattern so patients can receive life-saving therapy.
Why it matters
Early identification of Brugada syndrome allows patients to receive life-saving therapy.
What the AI did
A deep learning model was trained in two stages on 276 type 1 Brugada ECGs versus 276 non-Brugada ECGs, first learning right bundle branch block patterns and then transferring that learning to diagnose the type 1 Brugada pattern.
Results
not stated in source
Impact
Demonstrates feasibility of automated ECG screening for Brugada syndrome, though performance figures are not visible in the abstract.
Record
| Venue | Canadian Journal of Cardiology |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Chih‐Min Liu, Chien‐Liang Liu, Kai-Wen Hu, Vincent S. M. Tseng, Shih‐Lin Chang, Yenn‐Jiang Lin, Li‐Wei Lo, Fa‐Po Chung et al. |
| Citations | 55 (OpenAlex, at import time) |
| References | 40 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1016/j.cjca.2021.08.014 |
| Open access | gold |
| Keywords | Brugada syndrome, ECG, deep learning, transfer learning, cardiac screening |
Importance rating
significant — thousands to millions affected
Abstract states Brugada syndrome is a major cause of sudden cardiac death in young people and early identification enables life-saving therapy; rare condition limits population scale.