Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis

This work proposes a learning model to predict the outcome of electrical defibrillation from ECG signals in ventricular fibrillation (VF) periods, which is a lethal situation happening when a patient is suffering cardiac arrest. An animal experiment of rats is conducted to obtain the ECG signals and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dean-Chang Ling, Min-Shan Tsai, Dean-An Ling, Shang-Ho Tsai
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Ventricular fibrillation electrical defibrillation outcome prediction machine learning statistical model clinical inference via learning Electric apparatus and materials. Electric circuits. Electric networks TK452-454.4
Acceso en línea:	https://doaj.org/article/89ed548831e547019422747a4dcd5b37
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:89ed548831e547019422747a4dcd5b37
record_format	dspace
spelling	oai:doaj.org-article:89ed548831e547019422747a4dcd5b372021-12-04T00:00:18ZPredicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis2644-122510.1109/OJCAS.2021.3127270https://doaj.org/article/89ed548831e547019422747a4dcd5b372021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611783/https://doaj.org/toc/2644-1225This work proposes a learning model to predict the outcome of electrical defibrillation from ECG signals in ventricular fibrillation (VF) periods, which is a lethal situation happening when a patient is suffering cardiac arrest. An animal experiment of rats is conducted to obtain the ECG signals and necessary information for this study. This proposed model only extracts one feature from the ECG signals and enjoys low computational complexity at both training and testing stages. The statistics of this extracted single feature is further analyzed, and mathematical closed-form formulas for several interesting performance indices including the sensitivity, specificity, accuracy, precision and Area Under the Curve (AUC) are obtained to gain more insights of the proposed system. Moreover, the extracted feature can be treated as a linear combination of individual frequency components of the ECG signal, where the combining coefficients of the linear combination may show informative clinical inference. Frequencies corresponding to large trained combining coefficients imply that they contribute more in distinguishing the defibrillation outcome, and vice versa. As a result, important frequencies of the ECG signals can be identified and insignificant frequencies can also be filtered out by the proposed training. Simulation results corroborate the analytical results, and show that the proposed scheme greatly outperforms several competitive learning models and traditional methods in terms of testing accuracy and computational complexity.Dean-Chang LingMin-Shan TsaiDean-An LingShang-Ho TsaiIEEEarticleVentricular fibrillationelectrical defibrillationoutcome predictionmachine learningstatistical modelclinical inference via learningElectric apparatus and materials. Electric circuits. Electric networksTK452-454.4ENIEEE Open Journal of Circuits and Systems, Vol 2, Pp 686-699 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Ventricular fibrillation electrical defibrillation outcome prediction machine learning statistical model clinical inference via learning Electric apparatus and materials. Electric circuits. Electric networks TK452-454.4
spellingShingle	Ventricular fibrillation electrical defibrillation outcome prediction machine learning statistical model clinical inference via learning Electric apparatus and materials. Electric circuits. Electric networks TK452-454.4 Dean-Chang Ling Min-Shan Tsai Dean-An Ling Shang-Ho Tsai Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
description	This work proposes a learning model to predict the outcome of electrical defibrillation from ECG signals in ventricular fibrillation (VF) periods, which is a lethal situation happening when a patient is suffering cardiac arrest. An animal experiment of rats is conducted to obtain the ECG signals and necessary information for this study. This proposed model only extracts one feature from the ECG signals and enjoys low computational complexity at both training and testing stages. The statistics of this extracted single feature is further analyzed, and mathematical closed-form formulas for several interesting performance indices including the sensitivity, specificity, accuracy, precision and Area Under the Curve (AUC) are obtained to gain more insights of the proposed system. Moreover, the extracted feature can be treated as a linear combination of individual frequency components of the ECG signal, where the combining coefficients of the linear combination may show informative clinical inference. Frequencies corresponding to large trained combining coefficients imply that they contribute more in distinguishing the defibrillation outcome, and vice versa. As a result, important frequencies of the ECG signals can be identified and insignificant frequencies can also be filtered out by the proposed training. Simulation results corroborate the analytical results, and show that the proposed scheme greatly outperforms several competitive learning models and traditional methods in terms of testing accuracy and computational complexity.
format	article
author	Dean-Chang Ling Min-Shan Tsai Dean-An Ling Shang-Ho Tsai
author_facet	Dean-Chang Ling Min-Shan Tsai Dean-An Ling Shang-Ho Tsai
author_sort	Dean-Chang Ling
title	Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
title_short	Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
title_full	Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
title_fullStr	Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
title_full_unstemmed	Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis
title_sort	predicting ventricular defibrillation results using learning models: a design practice and performance analysis
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/89ed548831e547019422747a4dcd5b37
work_keys_str_mv	AT deanchangling predictingventriculardefibrillationresultsusinglearningmodelsadesignpracticeandperformanceanalysis AT minshantsai predictingventriculardefibrillationresultsusinglearningmodelsadesignpracticeandperformanceanalysis AT deananling predictingventriculardefibrillationresultsusinglearningmodelsadesignpracticeandperformanceanalysis AT shanghotsai predictingventriculardefibrillationresultsusinglearningmodelsadesignpracticeandperformanceanalysis
_version_	1718373042267095040

Predicting Ventricular Defibrillation Results Using Learning Models: A Design Practice and Performance Analysis

Ejemplares similares