### Abstract

Variability of factors exerting influence on arrhythmia origination leads to the appearance of polimodal distribution in sample space. Therefore, for the approximation of feature distribution, distribution mixture is used. To estimate the number of mixture components and to determine its parameters, cluster algorithm is used. The basic task of the algorithm is to identify the accumulation of vectors in the parallelepiped of their distribution. The accumulations of points are determined by testing statistical hypothesis of uniformity. On the basis of accumulations, clusters are formed and the parameters of normal mixtures of classes are estimated. Analysis of error matrix for recognition of mixture, enable to establish the parameters of the decision rule. The above algorithm was applied for recognition and prognosis of vulnerability of reentry and focal source in experiments on the right rabbit's atrium by using the electrophysiological parameters. We studied 30 cases of reentry, 36 cases of focal sources and 165 - arrhythmia - free cases. As a result, we established the 7-class normal mixture which enabled a more effective (96.4%) recognition of the vulnerability types and 89.9% prognosis by features: increase in latency (Θ), width of the interval of latency distribution, ratio (Θ)/R, where R- refractory period.

Original language | English (US) |
---|---|

Title of host publication | Biomedical Sciences Instrumentation |

Publisher | Publ by Instrument Society of America |

Pages | 21-26 |

Number of pages | 6 |

Volume | 30 |

ISBN (Print) | 1556174985 |

State | Published - 1994 |

Externally published | Yes |

Event | Proceedings of the 31st Annual Rocky Mountain Bioengineering Symposium (RMBS) - Manhattan, KS, USA Duration: Apr 22 1994 → Apr 23 1994 |

### Other

Other | Proceedings of the 31st Annual Rocky Mountain Bioengineering Symposium (RMBS) |
---|---|

City | Manhattan, KS, USA |

Period | 4/22/94 → 4/23/94 |

### Fingerprint

### Keywords

- Cluster analysis
- Myocardial vulnerability
- Normal mixture
- Statistical recognition system

### ASJC Scopus subject areas

- Hardware and Architecture

### Cite this

*Biomedical Sciences Instrumentation*(Vol. 30, pp. 21-26). Publ by Instrument Society of America.

**Use of cluster analysis technique for computerized recognition and prognosis of myocardial vulnerability.** / Saferis, V.; Valiunas, V.; Vilkauskas, L.; Bukauskas, F.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Biomedical Sciences Instrumentation.*vol. 30, Publ by Instrument Society of America, pp. 21-26, Proceedings of the 31st Annual Rocky Mountain Bioengineering Symposium (RMBS), Manhattan, KS, USA, 4/22/94.

}

TY - GEN

T1 - Use of cluster analysis technique for computerized recognition and prognosis of myocardial vulnerability

AU - Saferis, V.

AU - Valiunas, V.

AU - Vilkauskas, L.

AU - Bukauskas, F.

PY - 1994

Y1 - 1994

N2 - Variability of factors exerting influence on arrhythmia origination leads to the appearance of polimodal distribution in sample space. Therefore, for the approximation of feature distribution, distribution mixture is used. To estimate the number of mixture components and to determine its parameters, cluster algorithm is used. The basic task of the algorithm is to identify the accumulation of vectors in the parallelepiped of their distribution. The accumulations of points are determined by testing statistical hypothesis of uniformity. On the basis of accumulations, clusters are formed and the parameters of normal mixtures of classes are estimated. Analysis of error matrix for recognition of mixture, enable to establish the parameters of the decision rule. The above algorithm was applied for recognition and prognosis of vulnerability of reentry and focal source in experiments on the right rabbit's atrium by using the electrophysiological parameters. We studied 30 cases of reentry, 36 cases of focal sources and 165 - arrhythmia - free cases. As a result, we established the 7-class normal mixture which enabled a more effective (96.4%) recognition of the vulnerability types and 89.9% prognosis by features: increase in latency (Θ), width of the interval of latency distribution, ratio (Θ)/R, where R- refractory period.

AB - Variability of factors exerting influence on arrhythmia origination leads to the appearance of polimodal distribution in sample space. Therefore, for the approximation of feature distribution, distribution mixture is used. To estimate the number of mixture components and to determine its parameters, cluster algorithm is used. The basic task of the algorithm is to identify the accumulation of vectors in the parallelepiped of their distribution. The accumulations of points are determined by testing statistical hypothesis of uniformity. On the basis of accumulations, clusters are formed and the parameters of normal mixtures of classes are estimated. Analysis of error matrix for recognition of mixture, enable to establish the parameters of the decision rule. The above algorithm was applied for recognition and prognosis of vulnerability of reentry and focal source in experiments on the right rabbit's atrium by using the electrophysiological parameters. We studied 30 cases of reentry, 36 cases of focal sources and 165 - arrhythmia - free cases. As a result, we established the 7-class normal mixture which enabled a more effective (96.4%) recognition of the vulnerability types and 89.9% prognosis by features: increase in latency (Θ), width of the interval of latency distribution, ratio (Θ)/R, where R- refractory period.

KW - Cluster analysis

KW - Myocardial vulnerability

KW - Normal mixture

KW - Statistical recognition system

UR - http://www.scopus.com/inward/record.url?scp=0028582036&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028582036&partnerID=8YFLogxK

M3 - Conference contribution

C2 - 7948638

AN - SCOPUS:0028582036

SN - 1556174985

VL - 30

SP - 21

EP - 26

BT - Biomedical Sciences Instrumentation

PB - Publ by Instrument Society of America

ER -