Identification of atrial fibrillation mechanisms and arrhythmic patterns in body surface potential mapping systems

• Grant number: 17/19775-3
• Support Opportunities: Scholarships in Brazil - Master
• Start date: May 01, 2018
• End date: April 30, 2020
• Field of knowledge: Engineering - Biomedical Engineering - Bioengineering
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: João Loures Salinet Júnior
• Grantee: Victor Gonçalves Marques
• Host Institution: Centro de Engenharia, Modelagem e Ciências Sociais Aplicadas (CECS). Universidade Federal do ABC (UFABC). Ministério da Educação (Brasil). Santo André , SP, Brazil

Abstract

Atrial fibrillation (AF) is the most common heart arrhythmia in the world. The mechanisms that cause and maintaing the AF are still controverse, with increased complexity when it persists for long time periods (persistent atrial fibrillation, persAF), being the success rate of the current treatments for these patients suboptimal. Non-invase body surface potential mapping (BSPM) systems have been used to guide personalized AF treatment. The application of computer assisted diagnosis in BSPM through machine learning is promising, given the interpretation complexity of its maps. This project aims to apply such techniques for the identification of mechanisms and arrhythmic patterns of persAF in BSPM signals and maps in order to favor a personalized approach to the development of treatment strategies. Computer models of the heart representing the electrophysiological behavior of AF will be used; the signals provenient of the model will go through preprocessing stages, BSPM map generation, extraction and selection of representative features in order to compact the information and classification with linear and non-linear methods, both supervised and unsupervised. Classification performance will be evaluated and the features will be studied under a clinical perspective, based on literature review, in order to associate them with the AF's phisiopathology. At the end the analysis will be expanded to real situations, using patient signals, where it can contribute to the improvement of personalized treatment and their overall life quality. (AU)

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

GONCALVES MARQUES, VICTOR; RODRIGO, MIGUEL; DE LA SALUD GUILLEM, MARIA; SALINET, JOAO. Characterization of atrial arrhythmias in body surface potential mapping: A computational study. COMPUTERS IN BIOLOGY AND MEDICINE, v. 127, DEC 2020. (17/19775-3)

MARQUES, VICTOR G.; RODRIGO, MIGUEL; GUILLEM, MARIA S.; SALINET, JOAO; IEEE. Classification and Location of Atrial Arrhythmic Mechanisms With Body Surface Potential Mapping. 2020 COMPUTING IN CARDIOLOGY, v. N/A, p. 4-pg., 2020-01-01. (17/19775-3)

MARQUES, V. G.; RODRIGO, M.; GUILLEM, M. S.; SALINET, J.. A robust wavelet-based approach for dominant frequency analysis of atrial fibrillation in body surface signals. Physiological Measurement, v. 41, n. 7, JUL 2020. (17/19775-3)

MARQUES, VICTOR G; RODRIGO, MIGUEL; GUILLEM, MARIA S.; SALINET, JOAO; IEEE. A Wavelet-Based Method for Non-Invasive Dominant Frequency Detection in Atrial Fibrillation. 2020 COMPUTING IN CARDIOLOGY, v. N/A, p. 4-pg., 2020-01-01. (17/19775-3)