Classificiation of Atrial Fibrillation Prone Patients Using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,

Mirela Ovreiu; Marc Petre; Daniel J. Simon; Daniel Sessler; C Allen Bashour

Classificiation of Atrial Fibrillation Prone Patients Using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,

Mirela Ovreiu, Marc Petre, Daniel J. Simon, Daniel Sessler, C Allen Bashour

Cleveland Clinic Foundation

Research output: Contribution to conference › Presentation

Abstract

Atrial Fibrillation (AF) is a significant clinical problem and the complications of cardiovascular postoperative AF often lead to longer hospital stays and higher heath care costs. The literature showed that AF may be preceded by changes in electrocardiogram (ECG) characteristics such as premature atrial activity, heart rate variability (HRV), and P-wave morphology. We hypothesize that the limitations of statistics-based attempts to predict AF occurrence may be overcome using a hybrid neuro-fuzzy prediction model that is better capable of uncovering complex, non-linear interactions between ECG parameters. We created a neuro-fuzzy network that was able to classify the patients into the control and AF groups with the performances: 99.42% sensitivity, 99.89% specificity, and 99.74% accuracy for 30 minutes just before AF onset.

Original language	American English
State	Published - Mar 1 2010
Event	AMA-IEEE Medical Technology Conference on Individualized Healthcare - Duration: Mar 1 2010 → …

Conference

Conference	AMA-IEEE Medical Technology Conference on Individualized Healthcare
Period	3/1/10 → …

Disciplines

Electrical and Computer Engineering

Access to Document

Classificiation of Atrial Fibrillation Prone Patients Using ElectFinal published version, 711 KBLicense: CC BY

Cite this

@conference{557f076df97e41e0b7bde5a5de572fa9,

title = "Classificiation of Atrial Fibrillation Prone Patients Using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,",

abstract = " Atrial Fibrillation (AF) is a significant clinical problem and the complications of cardiovascular postoperative AF often lead to longer hospital stays and higher heath care costs. The literature showed that AF may be preceded by changes in electrocardiogram (ECG) characteristics such as premature atrial activity, heart rate variability (HRV), and P-wave morphology. We hypothesize that the limitations of statistics-based attempts to predict AF occurrence may be overcome using a hybrid neuro-fuzzy prediction model that is better capable of uncovering complex, non-linear interactions between ECG parameters. We created a neuro-fuzzy network that was able to classify the patients into the control and AF groups with the performances: 99.42\% sensitivity, 99.89\% specificity, and 99.74\% accuracy for 30 minutes just before AF onset.",

author = "Mirela Ovreiu and Marc Petre and Simon, \{Daniel J.\} and Daniel Sessler and Bashour, \{C Allen\}",

note = "M. Ovreiu, M. Petre, D. Simon, D. Sessler, and C. Bashour, “Classification of Atrial Fibrillation prone Patients using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,” AMA-IEEE Medical Technology Conference on Individualized Healthcare, Washington, DC, March 2010; AMA-IEEE Medical Technology Conference on Individualized Healthcare ; Conference date: 01-03-2010",

year = "2010",

month = mar,

day = "1",

language = "American English",

}

TY - CONF

T1 - Classificiation of Atrial Fibrillation Prone Patients Using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,

AU - Ovreiu, Mirela

AU - Petre, Marc

AU - Simon, Daniel J.

AU - Sessler, Daniel

AU - Bashour, C Allen

N1 - M. Ovreiu, M. Petre, D. Simon, D. Sessler, and C. Bashour, “Classification of Atrial Fibrillation prone Patients using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,” AMA-IEEE Medical Technology Conference on Individualized Healthcare, Washington, DC, March 2010

PY - 2010/3/1

Y1 - 2010/3/1

N2 - Atrial Fibrillation (AF) is a significant clinical problem and the complications of cardiovascular postoperative AF often lead to longer hospital stays and higher heath care costs. The literature showed that AF may be preceded by changes in electrocardiogram (ECG) characteristics such as premature atrial activity, heart rate variability (HRV), and P-wave morphology. We hypothesize that the limitations of statistics-based attempts to predict AF occurrence may be overcome using a hybrid neuro-fuzzy prediction model that is better capable of uncovering complex, non-linear interactions between ECG parameters. We created a neuro-fuzzy network that was able to classify the patients into the control and AF groups with the performances: 99.42% sensitivity, 99.89% specificity, and 99.74% accuracy for 30 minutes just before AF onset.

AB - Atrial Fibrillation (AF) is a significant clinical problem and the complications of cardiovascular postoperative AF often lead to longer hospital stays and higher heath care costs. The literature showed that AF may be preceded by changes in electrocardiogram (ECG) characteristics such as premature atrial activity, heart rate variability (HRV), and P-wave morphology. We hypothesize that the limitations of statistics-based attempts to predict AF occurrence may be overcome using a hybrid neuro-fuzzy prediction model that is better capable of uncovering complex, non-linear interactions between ECG parameters. We created a neuro-fuzzy network that was able to classify the patients into the control and AF groups with the performances: 99.42% sensitivity, 99.89% specificity, and 99.74% accuracy for 30 minutes just before AF onset.

UR - https://engagedscholarship.csuohio.edu/enece_facpub/192

M3 - Presentation

T2 - AMA-IEEE Medical Technology Conference on Individualized Healthcare

Y2 - 1 March 2010

ER -

Classificiation of Atrial Fibrillation Prone Patients Using Electrocardiographic Parameters in Neuro-Fuzzy Modeling,

Abstract

Conference

Disciplines

Access to Document

Other files and links

Cite this