Brugada Syndrome (BrS) is a rare but potentially fatal cardiac arrhythmia disorder first identified by the Brugada brothers in 1992. Characterized by distinct electrocardiogram (ECG) abnormalities, BrS is linked to an increased risk of sudden cardiac death, particularly in young individuals with otherwise normal hearts. This study aims to develop a neural network model for accurately classifying Brugada ECG patterns to enhance automated diagnostic capabilities. A dataset of 592 digital ECGs was collected, comprising 61 ECGs from confirmed Brugada patients and 531 from healthy individuals or those with other pathologies. The neural network was trained and validated, demonstrating strong performance with high accuracy (96%), sensitivity (90%), and specificity (97%) on a test set consisting of 128 Brugada windows and 1041 No Brugada windows. The model’s performance metrics indicate robust classification capabilities and weight analysis of the network showed coherence with clinical guidelines, particularly in its focus on the ST segment. The model was also tested on a second dataset of 25 digitized paper-based Brugada ECGs, achieving reasonable performance despite artifacts. This research validates the use of neural networks in classifying Brugada ECG patterns, highlighting the potential of AI-driven methodologies to improve diagnostic tools and patient outcomes.