A Support System for ECG Segmentation Based on Hidden Markov Models

Author

Thomas, J. ; Rose, C. ; Charpillet, F.

Author_Institution

Cardiabase, Nancy

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

3228

Lastpage

3231

Abstract

Pharmaceutic studies require to analyze thousands of ECGs in order to evaluate the side effects of a new drug. In this paper we present a new support system based on the use of probabilistic models for automatic ECG segmentation. We used a bayesian HMM clustering algorithm to partition the training base, and we improved the method by using a multichannel segmentation. We present a statistical analysis of the results where we compare different automatic methods to the segmentation of the cardiologist as a gold standard.

Keywords

drugs; electrocardiography; hidden Markov models; medical signal processing; pattern clustering; statistical analysis; Bayesian HMM clustering algorithm; automatic ECG segmentation; drug side effects; hidden Markov models; multichannel segmentation; statistical analysis; Bayesian methods; Cardiology; Clustering algorithms; Continuous wavelet transforms; Discrete wavelet transforms; Drugs; Electrocardiography; Hidden Markov models; Partitioning algorithms; Proposals; Algorithms; Arrhythmias, Cardiac; Artificial Intelligence; Computer Simulation; Diagnosis, Computer-Assisted; Electrocardiography; Heart Rate; Humans; Markov Chains; Models, Cardiovascular; Models, Statistical; Pattern Recognition, Automated; Software;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4353017

Filename

4353017