A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes

JD Diaz, C Gonzalez, OJ Escalona

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

The aim of this work is to predict the spontaneous termination of atrial fibrillation (AF) episodes. The database includes three record groups: non-terminating AF (N), AF that terminates one minute after recording end (S), and AF that terminates immediately after recording end (T). A first goal consisted on separating N from T group records (event 1), and a second, for separating S from T records (event 2). A Support Vector Machine was used for the classification problem. For event 1, four indexes were extracted: the atrial fibrillatory frequency (AFF) and the mean, standard deviation, and approximate entropy of RR intervals. For event 2, the AFF, the energy of the 3-7 Hz and 7-11 Hz bands, from the ten and five final seconds of the records, were used. The groups were divided in two sets: learning and test. For event 1, a 100% in learning, and 86.66% in test set were correctly classified. For the event 2, we classified 100% in the learning, and 80% in the test set.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages949-952
Number of pages4
Volume33
Publication statusPublished - 15 Dec 2006
EventComputers in Cardiology 2006, Valencia, Spain - Valencia, Spain
Duration: 15 Dec 2006 → …

Conference

ConferenceComputers in Cardiology 2006, Valencia, Spain
Period15/12/06 → …

Fingerprint

Atrial Fibrillation
Learning
Entropy
Databases
Support Vector Machine

Keywords

  • Cardiology
  • Learning systems
  • Standards
  • Support vector machines
  • Testing
  • Vectors
  • Approximate entropy
  • Atrial fibrillation
  • Paroxysmal atrial fibrillation
  • R-R interval
  • Standard deviation
  • medical signal processing
  • signal classification.

Cite this

Diaz, JD., Gonzalez, C., & Escalona, OJ. (2006). A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes. In Unknown Host Publication (Vol. 33, pp. 949-952)
@inproceedings{f2ca4d93b7fe484f8693be0c99f28d0d,
title = "A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes",
abstract = "The aim of this work is to predict the spontaneous termination of atrial fibrillation (AF) episodes. The database includes three record groups: non-terminating AF (N), AF that terminates one minute after recording end (S), and AF that terminates immediately after recording end (T). A first goal consisted on separating N from T group records (event 1), and a second, for separating S from T records (event 2). A Support Vector Machine was used for the classification problem. For event 1, four indexes were extracted: the atrial fibrillatory frequency (AFF) and the mean, standard deviation, and approximate entropy of RR intervals. For event 2, the AFF, the energy of the 3-7 Hz and 7-11 Hz bands, from the ten and five final seconds of the records, were used. The groups were divided in two sets: learning and test. For event 1, a 100{\%} in learning, and 86.66{\%} in test set were correctly classified. For the event 2, we classified 100{\%} in the learning, and 80{\%} in the test set.",
keywords = "Cardiology, Learning systems, Standards, Support vector machines, Testing, Vectors, Approximate entropy, Atrial fibrillation, Paroxysmal atrial fibrillation, R-R interval, Standard deviation, medical signal processing, signal classification.",
author = "JD Diaz and C Gonzalez and OJ Escalona",
year = "2006",
month = "12",
day = "15",
language = "English",
isbn = "978-1-4244-2532-7",
volume = "33",
pages = "949--952",
booktitle = "Unknown Host Publication",

}

Diaz, JD, Gonzalez, C & Escalona, OJ 2006, A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes. in Unknown Host Publication. vol. 33, pp. 949-952, Computers in Cardiology 2006, Valencia, Spain, 15/12/06.

A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes. / Diaz, JD; Gonzalez, C; Escalona, OJ.

Unknown Host Publication. Vol. 33 2006. p. 949-952.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A support vector machine for predicting spontaneous termination of paroxysmal atrial fibrillation episodes

AU - Diaz, JD

AU - Gonzalez, C

AU - Escalona, OJ

PY - 2006/12/15

Y1 - 2006/12/15

N2 - The aim of this work is to predict the spontaneous termination of atrial fibrillation (AF) episodes. The database includes three record groups: non-terminating AF (N), AF that terminates one minute after recording end (S), and AF that terminates immediately after recording end (T). A first goal consisted on separating N from T group records (event 1), and a second, for separating S from T records (event 2). A Support Vector Machine was used for the classification problem. For event 1, four indexes were extracted: the atrial fibrillatory frequency (AFF) and the mean, standard deviation, and approximate entropy of RR intervals. For event 2, the AFF, the energy of the 3-7 Hz and 7-11 Hz bands, from the ten and five final seconds of the records, were used. The groups were divided in two sets: learning and test. For event 1, a 100% in learning, and 86.66% in test set were correctly classified. For the event 2, we classified 100% in the learning, and 80% in the test set.

AB - The aim of this work is to predict the spontaneous termination of atrial fibrillation (AF) episodes. The database includes three record groups: non-terminating AF (N), AF that terminates one minute after recording end (S), and AF that terminates immediately after recording end (T). A first goal consisted on separating N from T group records (event 1), and a second, for separating S from T records (event 2). A Support Vector Machine was used for the classification problem. For event 1, four indexes were extracted: the atrial fibrillatory frequency (AFF) and the mean, standard deviation, and approximate entropy of RR intervals. For event 2, the AFF, the energy of the 3-7 Hz and 7-11 Hz bands, from the ten and five final seconds of the records, were used. The groups were divided in two sets: learning and test. For event 1, a 100% in learning, and 86.66% in test set were correctly classified. For the event 2, we classified 100% in the learning, and 80% in the test set.

KW - Cardiology

KW - Learning systems

KW - Standards

KW - Support vector machines

KW - Testing

KW - Vectors

KW - Approximate entropy

KW - Atrial fibrillation

KW - Paroxysmal atrial fibrillation

KW - R-R interval

KW - Standard deviation

KW - medical signal processing

KW - signal classification.

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=4512010&sortType%3Dasc_p_Publication_Year%26queryText%3Descalona%2C+o

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=4512010&sortType%3Dasc_p_Publication_Year%26queryText%3Descalona%2C+o

M3 - Conference contribution

SN - 978-1-4244-2532-7

VL - 33

SP - 949

EP - 952

BT - Unknown Host Publication

ER -