Limits...
An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects.

Kim J, Min SD, Lee M - Biomed Eng Online (2011)

Bottom Line: We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects.The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%.And it significantly reduces the amount of intervention needed by physicians.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Electronic and Electrical Engineering, Yonsei University, Seoul, Korea.

ABSTRACT

Background: Numerous studies have been conducted regarding a heartbeat classification algorithm over the past several decades. However, many algorithms have also been studied to acquire robust performance, as biosignals have a large amount of variation among individuals. Various methods have been proposed to reduce the differences coming from personal characteristics, but these expand the differences caused by arrhythmia.

Methods: In this paper, an arrhythmia classification algorithm using a dedicated wavelet adapted to individual subjects is proposed. We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects. The proposed algorithm utilizes morphological filtering and a continuous wavelet transform with a dedicated wavelet. A principal component analysis and linear discriminant analysis were utilized to compress the morphological data transformed by the dedicated wavelets. An extreme learning machine was used as a classifier in the proposed algorithm.

Results: A performance evaluation was conducted with the MIT-BIH arrhythmia database. The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%.

Conclusions: The proposed algorithm achieves better accuracy than other state-of-the-art algorithms with no intrasubject between the training and evaluation datasets. And it significantly reduces the amount of intervention needed by physicians.

Show MeSH

Related in: MedlinePlus

Examples of the analysis of subjects 212 and 231 in the MIT-BIH arrhythmia database using a dedicated wavelet. (A) The waveform of subject 212's normal beat, (B) The waveform of subject 212's right bundle branch block(RBBB), (C) The scalogram of subject 212's normal beat using the dedicated wavelet, (D) The scalogram of subject 212's RBBB using the dedicated wavelet, (E) The waveform of subject 231's normal beat, (F) The waveform of subject 231's RBBB, (G) The scalogram of subject 231's normal beat using the dedicated wavelet, (H) The scalogram of subject 231's RBBB using the dedicated wavelet
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3142238&req=5

Figure 4: Examples of the analysis of subjects 212 and 231 in the MIT-BIH arrhythmia database using a dedicated wavelet. (A) The waveform of subject 212's normal beat, (B) The waveform of subject 212's right bundle branch block(RBBB), (C) The scalogram of subject 212's normal beat using the dedicated wavelet, (D) The scalogram of subject 212's RBBB using the dedicated wavelet, (E) The waveform of subject 231's normal beat, (F) The waveform of subject 231's RBBB, (G) The scalogram of subject 231's normal beat using the dedicated wavelet, (H) The scalogram of subject 231's RBBB using the dedicated wavelet

Mentions: In addition, while TemplateM can only evaluate the similarity between the template heartbeat and the input signal, the proposed method can analyze other characteristics. There are ECG morphologies and scalograms of a normal heartbeat and the right bundle branch block (RBBB) shown in Feature 4. Both the normal heartbeat and RBBB are included in the N class. However, the morphology of RBBB has a wide and deep S wave owing to its slow right ventricular depolarization (Figures 4(b) and 4(f)).


An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects.

Kim J, Min SD, Lee M - Biomed Eng Online (2011)

Examples of the analysis of subjects 212 and 231 in the MIT-BIH arrhythmia database using a dedicated wavelet. (A) The waveform of subject 212's normal beat, (B) The waveform of subject 212's right bundle branch block(RBBB), (C) The scalogram of subject 212's normal beat using the dedicated wavelet, (D) The scalogram of subject 212's RBBB using the dedicated wavelet, (E) The waveform of subject 231's normal beat, (F) The waveform of subject 231's RBBB, (G) The scalogram of subject 231's normal beat using the dedicated wavelet, (H) The scalogram of subject 231's RBBB using the dedicated wavelet
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3142238&req=5

Figure 4: Examples of the analysis of subjects 212 and 231 in the MIT-BIH arrhythmia database using a dedicated wavelet. (A) The waveform of subject 212's normal beat, (B) The waveform of subject 212's right bundle branch block(RBBB), (C) The scalogram of subject 212's normal beat using the dedicated wavelet, (D) The scalogram of subject 212's RBBB using the dedicated wavelet, (E) The waveform of subject 231's normal beat, (F) The waveform of subject 231's RBBB, (G) The scalogram of subject 231's normal beat using the dedicated wavelet, (H) The scalogram of subject 231's RBBB using the dedicated wavelet
Mentions: In addition, while TemplateM can only evaluate the similarity between the template heartbeat and the input signal, the proposed method can analyze other characteristics. There are ECG morphologies and scalograms of a normal heartbeat and the right bundle branch block (RBBB) shown in Feature 4. Both the normal heartbeat and RBBB are included in the N class. However, the morphology of RBBB has a wide and deep S wave owing to its slow right ventricular depolarization (Figures 4(b) and 4(f)).

Bottom Line: We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects.The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%.And it significantly reduces the amount of intervention needed by physicians.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Electronic and Electrical Engineering, Yonsei University, Seoul, Korea.

ABSTRACT

Background: Numerous studies have been conducted regarding a heartbeat classification algorithm over the past several decades. However, many algorithms have also been studied to acquire robust performance, as biosignals have a large amount of variation among individuals. Various methods have been proposed to reduce the differences coming from personal characteristics, but these expand the differences caused by arrhythmia.

Methods: In this paper, an arrhythmia classification algorithm using a dedicated wavelet adapted to individual subjects is proposed. We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects. The proposed algorithm utilizes morphological filtering and a continuous wavelet transform with a dedicated wavelet. A principal component analysis and linear discriminant analysis were utilized to compress the morphological data transformed by the dedicated wavelets. An extreme learning machine was used as a classifier in the proposed algorithm.

Results: A performance evaluation was conducted with the MIT-BIH arrhythmia database. The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%.

Conclusions: The proposed algorithm achieves better accuracy than other state-of-the-art algorithms with no intrasubject between the training and evaluation datasets. And it significantly reduces the amount of intervention needed by physicians.

Show MeSH
Related in: MedlinePlus