In the present study recurrent neural networks, in particular Echo State Networks (ESNs), have been applied for the prediction of Brugada Syndrome (BrS) from electrocardiogram (ECG) signals. The research lays its foundations in BrAID (Brugada syndrome and Artificial Intelligence applications to Diagnosis), a project aimed at developing an innovative system for early detection and classification of BrS Type 1. The ultimate objective of the BrAID platform is to help clinicians to improve the BrS diagnosis process, to detect a pattern in ECG, and to combine them with multi-omics information through Artificial Intelligence (AI) - Machine Learning (ML) models, such as ESNs. We report novel preliminary results of this approach, presenting the first baseline results, in terms of accuracy, for BrS recognition using ECG analysis, with the application of ESNs. Such results are particularly encouraging and may shed light on the possibility of using this model as a computational intelligence clinical support system tool for healthcare applications.

A preliminary evaluation of Echo State Networks for Brugada syndrome classification

Gallicchio C.;Micheli A.;Ungaro E.;Vozzi F.
2021-01-01

Abstract

In the present study recurrent neural networks, in particular Echo State Networks (ESNs), have been applied for the prediction of Brugada Syndrome (BrS) from electrocardiogram (ECG) signals. The research lays its foundations in BrAID (Brugada syndrome and Artificial Intelligence applications to Diagnosis), a project aimed at developing an innovative system for early detection and classification of BrS Type 1. The ultimate objective of the BrAID platform is to help clinicians to improve the BrS diagnosis process, to detect a pattern in ECG, and to combine them with multi-omics information through Artificial Intelligence (AI) - Machine Learning (ML) models, such as ESNs. We report novel preliminary results of this approach, presenting the first baseline results, in terms of accuracy, for BrS recognition using ECG analysis, with the application of ESNs. Such results are particularly encouraging and may shed light on the possibility of using this model as a computational intelligence clinical support system tool for healthcare applications.
2021
978-1-7281-9048-8
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/1135886
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 0
social impact