Complexity and Similarity Analysis of Heart Sound for Cardiovascular Disease Detection

Boomadevi Sekar, Jia Yi Dou, Bin Bin Fu, Xiao Lei Fei, Ming Chui Dong

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Heart auscultation signal has served as an important primary symptom to identify pathological condition of cardiovascular system for a long time. However, clinical capabilities to properly analyze Heart Sound (HS) have regressed recently. Thus, a new approach for automated Cardiovascular Disease (CVD) diagnosis based on complexity and similarity analysis of HS is presented. The relevant technologies namely, Musical Instrument Digital Interface (MIDI) coding and N-gram encoding are utilized for feature extraction and pattern encoding of HS. Lempel and Ziv (LZ) complexity and Super-symmetric Comparison Distance (SCD) similarity measure are used to measure the complexity and similarity between two HSs individually. To identify specific problems and important attributes required for HS analysis using the proposed approach, various simulated HS signals are generated and critically tested. The effect of change in amplitude, heart rate and length of HS record are identified on the diagnosis results and their thresholds or tolerances are predefined. Through such explored results, HS records of patients with different physiological characteristics which are practically incomparable are made comparable. The final testing results of such a novel approach with an average diagnostic accuracy above 70% in identifying some CVDs through comparing similarities of pathological conditions of HS with ones in benchmark database (DB) proves its feasibility and availability.
LanguageEnglish
Pages316-322
Number of pages7
JournalBiotechnology
Volume10
Issue number4
DOIs
Publication statusPublished - 2011

Fingerprint

Acoustic waves
Musical instruments
Cardiovascular system
Feature extraction
Chemical vapor deposition
Availability
Testing

Cite this

Sekar, Boomadevi ; Dou, Jia Yi ; Fu, Bin Bin ; Fei, Xiao Lei ; Dong, Ming Chui. / Complexity and Similarity Analysis of Heart Sound for Cardiovascular Disease Detection. In: Biotechnology. 2011 ; Vol. 10, No. 4. pp. 316-322.
@article{6e881f84b43641af8c95b069cfd398cc,
title = "Complexity and Similarity Analysis of Heart Sound for Cardiovascular Disease Detection",
abstract = "Heart auscultation signal has served as an important primary symptom to identify pathological condition of cardiovascular system for a long time. However, clinical capabilities to properly analyze Heart Sound (HS) have regressed recently. Thus, a new approach for automated Cardiovascular Disease (CVD) diagnosis based on complexity and similarity analysis of HS is presented. The relevant technologies namely, Musical Instrument Digital Interface (MIDI) coding and N-gram encoding are utilized for feature extraction and pattern encoding of HS. Lempel and Ziv (LZ) complexity and Super-symmetric Comparison Distance (SCD) similarity measure are used to measure the complexity and similarity between two HSs individually. To identify specific problems and important attributes required for HS analysis using the proposed approach, various simulated HS signals are generated and critically tested. The effect of change in amplitude, heart rate and length of HS record are identified on the diagnosis results and their thresholds or tolerances are predefined. Through such explored results, HS records of patients with different physiological characteristics which are practically incomparable are made comparable. The final testing results of such a novel approach with an average diagnostic accuracy above 70{\%} in identifying some CVDs through comparing similarities of pathological conditions of HS with ones in benchmark database (DB) proves its feasibility and availability.",
author = "Boomadevi Sekar and Dou, {Jia Yi} and Fu, {Bin Bin} and Fei, {Xiao Lei} and Dong, {Ming Chui}",
year = "2011",
doi = "10.3923/biotech.2011.316.322",
language = "English",
volume = "10",
pages = "316--322",
journal = "Biotechnology",
issn = "1682-296X",
publisher = "Asian Network for Scientific Information",
number = "4",

}

Complexity and Similarity Analysis of Heart Sound for Cardiovascular Disease Detection. / Sekar, Boomadevi; Dou, Jia Yi ; Fu, Bin Bin ; Fei, Xiao Lei; Dong, Ming Chui.

In: Biotechnology, Vol. 10, No. 4, 2011, p. 316-322.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Complexity and Similarity Analysis of Heart Sound for Cardiovascular Disease Detection

AU - Sekar, Boomadevi

AU - Dou, Jia Yi

AU - Fu, Bin Bin

AU - Fei, Xiao Lei

AU - Dong, Ming Chui

PY - 2011

Y1 - 2011

N2 - Heart auscultation signal has served as an important primary symptom to identify pathological condition of cardiovascular system for a long time. However, clinical capabilities to properly analyze Heart Sound (HS) have regressed recently. Thus, a new approach for automated Cardiovascular Disease (CVD) diagnosis based on complexity and similarity analysis of HS is presented. The relevant technologies namely, Musical Instrument Digital Interface (MIDI) coding and N-gram encoding are utilized for feature extraction and pattern encoding of HS. Lempel and Ziv (LZ) complexity and Super-symmetric Comparison Distance (SCD) similarity measure are used to measure the complexity and similarity between two HSs individually. To identify specific problems and important attributes required for HS analysis using the proposed approach, various simulated HS signals are generated and critically tested. The effect of change in amplitude, heart rate and length of HS record are identified on the diagnosis results and their thresholds or tolerances are predefined. Through such explored results, HS records of patients with different physiological characteristics which are practically incomparable are made comparable. The final testing results of such a novel approach with an average diagnostic accuracy above 70% in identifying some CVDs through comparing similarities of pathological conditions of HS with ones in benchmark database (DB) proves its feasibility and availability.

AB - Heart auscultation signal has served as an important primary symptom to identify pathological condition of cardiovascular system for a long time. However, clinical capabilities to properly analyze Heart Sound (HS) have regressed recently. Thus, a new approach for automated Cardiovascular Disease (CVD) diagnosis based on complexity and similarity analysis of HS is presented. The relevant technologies namely, Musical Instrument Digital Interface (MIDI) coding and N-gram encoding are utilized for feature extraction and pattern encoding of HS. Lempel and Ziv (LZ) complexity and Super-symmetric Comparison Distance (SCD) similarity measure are used to measure the complexity and similarity between two HSs individually. To identify specific problems and important attributes required for HS analysis using the proposed approach, various simulated HS signals are generated and critically tested. The effect of change in amplitude, heart rate and length of HS record are identified on the diagnosis results and their thresholds or tolerances are predefined. Through such explored results, HS records of patients with different physiological characteristics which are practically incomparable are made comparable. The final testing results of such a novel approach with an average diagnostic accuracy above 70% in identifying some CVDs through comparing similarities of pathological conditions of HS with ones in benchmark database (DB) proves its feasibility and availability.

U2 - 10.3923/biotech.2011.316.322

DO - 10.3923/biotech.2011.316.322

M3 - Article

VL - 10

SP - 316

EP - 322

JO - Biotechnology

T2 - Biotechnology

JF - Biotechnology

SN - 1682-296X

IS - 4

ER -