Weighted Conditional Random Fields for Supervised Interpatient Heartbeat Classification

This paper proposes a method for the automatic classification of heartbeats in an ECG signal. Since this task has specific characteristics such as time dependences between observations and a strong class unbalance, a specific classifier is proposed and evaluated on real ECG signals from the MIT arrh...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering 2012-01, Vol.59 (1), p.241-247
Main Authors: de Lannoy, Gaël, Francois, Damien, Delbeke, Jean, Verleysen, Michel
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Arrhythmias, Cardiac - diagnosis
Arrhythmias, Cardiac - physiopathology
Artificial Intelligence
Biological and medical sciences
Classification
Computerized, statistical medical data processing and models in biomedicine
conditional random fields (CRFs)
Diagnosis, Computer-Assisted - methods
electrocardiogram (ECG)
Electrocardiography
Electrocardiography - methods
Electrocardiography. Vectocardiography
Electrodiagnosis. Electric activity recording
Exact sciences and technology
Feature extraction
Heart beat
Heart Rate
Hidden Markov models
Humans
Information, signal and communications theory
Investigative techniques, diagnostic techniques (general aspects)
Medical management aid. Diagnosis aid
Medical sciences
Pathology
Pattern Recognition, Automated - methods
physiobank
Reproducibility of Results
Sensitivity and Specificity
Signal and communications theory
Signal representation. Spectral analysis
Signal, noise
Telecommunications and information theory
Training
unbalance
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a method for the automatic classification of heartbeats in an ECG signal. Since this task has specific characteristics such as time dependences between observations and a strong class unbalance, a specific classifier is proposed and evaluated on real ECG signals from the MIT arrhythmia database. This classifier is a weighted variant of the conditional random fields classifier. Experiments show that the proposed method outperforms previously reported heartbeat classification methods, especially for the pathological heartbeats.
ISSN:0018-9294
1558-2531
DOI:10.1109/TBME.2011.2171037