Caracterización en base a frecuencia y amplitud instantánea de Señales de ECGs para detección de Fibrilación Atrial
Date
2025-10-01
Journal Title
Journal ISSN
Volume Title
Publisher
Facultad Regional Buenos Aires
Abstract
El objetivo principal de esta investigación fue probar la capacidad de la descomposición en valores empíricos de señales de ECG de una sola derivación para caracterizar la fibrilación atrial. Para el estudio, se empleó una base de datos de amplia aceptación en la comunidad científica internacional. Con la metodología aquí propuesta se calculó la energía y la frecuencia instantáneas para los grupos de interés, es decir pacientes con FA diagnosticada y sujetos con registro sinusales normales. La simplicidad conceptual de las herramientas utilizadas hace que esta propuesta sea fácil de implementar, factible desde el punto de vista computacional y permite una interpretación clara de los resultados. Se presenta como un posible aporte para incorporar en los futuros modelos de machine learning que detecten de manera automática la patología estudiada.
The main objective of this investigation was to test the ability of the decomposition into empirical values of single-lead ECG signals to characterize atrial fibrillation. For the study, a database widely accepted in the international scientific community was used. With the methodology proposed here, instantaneous energy and frequency were calculated for the groups of interest, i.e. patients with diagnosed AF and subjects with normal sinus recordings. The conceptual simplicity of the tools used makes this proposal easy to apply, com- putationally feasible and allows a clear interpretation of the results. It is presented as a possible contribution to incorporate in future machine learning models that automatically detect the pathology studied.
The main objective of this investigation was to test the ability of the decomposition into empirical values of single-lead ECG signals to characterize atrial fibrillation. For the study, a database widely accepted in the international scientific community was used. With the methodology proposed here, instantaneous energy and frequency were calculated for the groups of interest, i.e. patients with diagnosed AF and subjects with normal sinus recordings. The conceptual simplicity of the tools used makes this proposal easy to apply, com- putationally feasible and allows a clear interpretation of the results. It is presented as a possible contribution to incorporate in future machine learning models that automatically detect the pathology studied.
Description
Keywords
Emd, Imf, Frecuencia instantánea, Amplitud instantánea, Hht, Ecg, Emd, Imf, Instantaneous frequency, Instantaneous amplitude, Hht, Ecg
Citation
Proyecciones, Vol.23 Nº 2
Collections
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwised noted, this item's license is described as info:eu-repo/semantics/openAccess