Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals

Quazi Abidur Rahman, Larisa Tereshchenko, Matthew Kongkatong, Theodore Abraham, M. Roselle Abraham, Hagit Shatkay

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    5 Citations (Scopus)

    Abstract

    Test based on electrocardiograms (ECG) that record the heart electrical activity can help in early detection of patients with hypertrophic cardiomyopathy (HCM) where the heart muscle is partially thickened and blood flow is (potentially fatally) obstructed. This paper presents a cardiovascular-patient classifier we developed to identify HCM patients using standard 10-seconds, 12-lead ECG signals. Patients are classified as having HCM if the majority of the heartbeats are recognized as HCM. Thus, the classifier's underlying task is to recognize individual heartbeats segmented from 12-lead ECG signals as HCM beats, where heartbeats from non-HCM cardiovascular patients are used as controls. We extracted 504 morphological and temporal features - both commonly used and newly-developed ones-from ECG signals for heartbeat classification. To assess classification performance, we trained and tested a random forest classifier and a support vector machine classifier using 5-fold cross validation. The patient-classification precision of both classifiers are close to 0.85. Recall (sensitivity) and specificity are approximately 0.90. We also conducted feature selection experiments by gradually removing the least informative features; the results show that a relatively small subset of 304 highly informative features can achieve performance measures comparable to that achieved by using the complete set of features.

    Original languageEnglish (US)
    Title of host publicationProceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages224-229
    Number of pages6
    ISBN (Print)9781479956692
    DOIs
    StatePublished - Dec 29 2014
    Event2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014 - Belfast, United Kingdom
    Duration: Nov 2 2014Nov 5 2014

    Other

    Other2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014
    CountryUnited Kingdom
    CityBelfast
    Period11/2/1411/5/14

    Fingerprint

    Hypertrophic Cardiomyopathy
    Electrocardiography
    Classifiers
    Lead
    Support vector machines
    Muscle
    Feature extraction
    Cardiomyopathies
    Blood
    Myocardium
    Sensitivity and Specificity
    Experiments

    Keywords

    • Electrocardiogram
    • Feature selection
    • Hypertrophic Cardiomyopathy
    • Machine learning methods
    • Patient classification

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Health Informatics

    Cite this

    Rahman, Q. A., Tereshchenko, L., Kongkatong, M., Abraham, T., Abraham, M. R., & Shatkay, H. (2014). Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals. In Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014 (pp. 224-229). [6999159] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2014.6999159

    Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals. / Rahman, Quazi Abidur; Tereshchenko, Larisa; Kongkatong, Matthew; Abraham, Theodore; Abraham, M. Roselle; Shatkay, Hagit.

    Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 224-229 6999159.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Rahman, QA, Tereshchenko, L, Kongkatong, M, Abraham, T, Abraham, MR & Shatkay, H 2014, Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals. in Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014., 6999159, Institute of Electrical and Electronics Engineers Inc., pp. 224-229, 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014, Belfast, United Kingdom, 11/2/14. https://doi.org/10.1109/BIBM.2014.6999159
    Rahman QA, Tereshchenko L, Kongkatong M, Abraham T, Abraham MR, Shatkay H. Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals. In Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 224-229. 6999159 https://doi.org/10.1109/BIBM.2014.6999159
    Rahman, Quazi Abidur ; Tereshchenko, Larisa ; Kongkatong, Matthew ; Abraham, Theodore ; Abraham, M. Roselle ; Shatkay, Hagit. / Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals. Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 224-229
    @inproceedings{24b283a522d2441fb81e51c3a239b752,
    title = "Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals",
    abstract = "Test based on electrocardiograms (ECG) that record the heart electrical activity can help in early detection of patients with hypertrophic cardiomyopathy (HCM) where the heart muscle is partially thickened and blood flow is (potentially fatally) obstructed. This paper presents a cardiovascular-patient classifier we developed to identify HCM patients using standard 10-seconds, 12-lead ECG signals. Patients are classified as having HCM if the majority of the heartbeats are recognized as HCM. Thus, the classifier's underlying task is to recognize individual heartbeats segmented from 12-lead ECG signals as HCM beats, where heartbeats from non-HCM cardiovascular patients are used as controls. We extracted 504 morphological and temporal features - both commonly used and newly-developed ones-from ECG signals for heartbeat classification. To assess classification performance, we trained and tested a random forest classifier and a support vector machine classifier using 5-fold cross validation. The patient-classification precision of both classifiers are close to 0.85. Recall (sensitivity) and specificity are approximately 0.90. We also conducted feature selection experiments by gradually removing the least informative features; the results show that a relatively small subset of 304 highly informative features can achieve performance measures comparable to that achieved by using the complete set of features.",
    keywords = "Electrocardiogram, Feature selection, Hypertrophic Cardiomyopathy, Machine learning methods, Patient classification",
    author = "Rahman, {Quazi Abidur} and Larisa Tereshchenko and Matthew Kongkatong and Theodore Abraham and Abraham, {M. Roselle} and Hagit Shatkay",
    year = "2014",
    month = "12",
    day = "29",
    doi = "10.1109/BIBM.2014.6999159",
    language = "English (US)",
    isbn = "9781479956692",
    pages = "224--229",
    booktitle = "Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals

    AU - Rahman, Quazi Abidur

    AU - Tereshchenko, Larisa

    AU - Kongkatong, Matthew

    AU - Abraham, Theodore

    AU - Abraham, M. Roselle

    AU - Shatkay, Hagit

    PY - 2014/12/29

    Y1 - 2014/12/29

    N2 - Test based on electrocardiograms (ECG) that record the heart electrical activity can help in early detection of patients with hypertrophic cardiomyopathy (HCM) where the heart muscle is partially thickened and blood flow is (potentially fatally) obstructed. This paper presents a cardiovascular-patient classifier we developed to identify HCM patients using standard 10-seconds, 12-lead ECG signals. Patients are classified as having HCM if the majority of the heartbeats are recognized as HCM. Thus, the classifier's underlying task is to recognize individual heartbeats segmented from 12-lead ECG signals as HCM beats, where heartbeats from non-HCM cardiovascular patients are used as controls. We extracted 504 morphological and temporal features - both commonly used and newly-developed ones-from ECG signals for heartbeat classification. To assess classification performance, we trained and tested a random forest classifier and a support vector machine classifier using 5-fold cross validation. The patient-classification precision of both classifiers are close to 0.85. Recall (sensitivity) and specificity are approximately 0.90. We also conducted feature selection experiments by gradually removing the least informative features; the results show that a relatively small subset of 304 highly informative features can achieve performance measures comparable to that achieved by using the complete set of features.

    AB - Test based on electrocardiograms (ECG) that record the heart electrical activity can help in early detection of patients with hypertrophic cardiomyopathy (HCM) where the heart muscle is partially thickened and blood flow is (potentially fatally) obstructed. This paper presents a cardiovascular-patient classifier we developed to identify HCM patients using standard 10-seconds, 12-lead ECG signals. Patients are classified as having HCM if the majority of the heartbeats are recognized as HCM. Thus, the classifier's underlying task is to recognize individual heartbeats segmented from 12-lead ECG signals as HCM beats, where heartbeats from non-HCM cardiovascular patients are used as controls. We extracted 504 morphological and temporal features - both commonly used and newly-developed ones-from ECG signals for heartbeat classification. To assess classification performance, we trained and tested a random forest classifier and a support vector machine classifier using 5-fold cross validation. The patient-classification precision of both classifiers are close to 0.85. Recall (sensitivity) and specificity are approximately 0.90. We also conducted feature selection experiments by gradually removing the least informative features; the results show that a relatively small subset of 304 highly informative features can achieve performance measures comparable to that achieved by using the complete set of features.

    KW - Electrocardiogram

    KW - Feature selection

    KW - Hypertrophic Cardiomyopathy

    KW - Machine learning methods

    KW - Patient classification

    UR - http://www.scopus.com/inward/record.url?scp=84922787239&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84922787239&partnerID=8YFLogxK

    U2 - 10.1109/BIBM.2014.6999159

    DO - 10.1109/BIBM.2014.6999159

    M3 - Conference contribution

    AN - SCOPUS:84922787239

    SN - 9781479956692

    SP - 224

    EP - 229

    BT - Proceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -