Politecnico di Torino (logo)

Brugada syndrome identification based on P-wave characteristics: a Machine Learning approach.

Beatrice Zanchi

Brugada syndrome identification based on P-wave characteristics: a Machine Learning approach.

Rel. Valentina Agostini, Francesca Dalia Faraci. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2021


Brugada syndrome is a hereditary disease with autosomal dominant transmission first observed in 1992 by Pedro and Josep Brugada. The disease causes disorders in the sodium channels within myocardiocytes. The altered function of these channels occurs more frequently in males than in females and generates a varied symptomatic picture. In milder cases, the patient presents with syncopes of arrhythmogenic origin and ventricular fibrillations that stop spontaneously during sleep. In more severe cases, the disease can lead to sudden cardiac death. The prevalence of the syndrome varies widely geographically, ranging from 5 cases per 10'000 people per year in Europe and the United States to 1 case per 2'500 people per year in South-East Asia. The diagnosis of the syndrome is made by observing the electrocardiographic picture presented in the patient's ECG, investigating the presence of the typical Brugada sign consisting of ST-segment elevation at the end of the QRS complex. The onset mechanism and diagnosis of the disease have for years suggested a purely ventricular origin of the syndrome. However, recent studies have revealed an altered atrial phenotype, suggesting that the electrophysiological mechanisms have been modified in the same way as in the ventricles. The aim of the present study was therefore to verify the feasibility of identifying Brugada syndrome based solely on atrial alterations visible on the ECG, and therefore related to the P-wave. In order to pursue this objective, AI-based models were developed to process the characteristics of the P-wave in order to identify the syndrome.

Relators: Valentina Agostini, Francesca Dalia Faraci
Academic year: 2021/22
Publication type: Electronic
Number of Pages: 110
Additional Information: Tesi secretata. Fulltext non presente
Corso di laurea: Corso di laurea magistrale in Ingegneria Biomedica
Classe di laurea: New organization > Master science > LM-21 - BIOMEDICAL ENGINEERING
Aziende collaboratrici: SUPSI
URI: http://webthesis.biblio.polito.it/id/eprint/21728
Modify record (reserved for operators) Modify record (reserved for operators)