Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources

Simon Kocbek, Lawrence Cavedon, David Martinez, Christopher Bain, Chris Mac Manus, Gholamreza Haffari, Ingrid Zukerman, Karin Verspoor

    Research output: Contribution to journal › Article › Research › peer-review

    Abstract

    Text and data mining play an important role in obtaining insights from Health and Hospital Information Systems. This paper presents a text mining system for detecting admissions marked as positive for several diseases: Lung Cancer, Breast Cancer, Colon Cancer, Secondary Malignant Neoplasm of Respiratory and Digestive Organs, Multiple Myeloma and Malignant Plasma Cell Neoplasms, Pneumonia, and Pulmonary Embolism. We specifically examine the effect of linking multiple data sources on text classification performance.
    Original languageEnglish
    Pages (from-to)158-167
    Number of pages10
    JournalJournal of Biomedical Informatics
    Volume64
    DOIs
    Publication statusPublished - 11 Oct 2016

    Keywords

    • Cancer record retrieval
    • Text mining
    • Natural Language Processing
    • Electronic Health Records
    • Radiology
    • Pathology

    Cite this

    Kocbek, Simon ; Cavedon, Lawrence ; Martinez, David ; Bain, Christopher ; Mac Manus, Chris ; Haffari, Gholamreza ; Zukerman, Ingrid ; Verspoor, Karin. / Text mining electronic hospital records to automatically classify admissions against disease : Measuring the impact of linking data sources. In: Journal of Biomedical Informatics. 2016 ; Vol. 64. pp. 158-167.
    @article{73ae62be30b24a5eada53b3fb860a508,
    title = "Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources",
    abstract = "Text and data mining play an important role in obtaining insights from Health and Hospital Information Systems. This paper presents a text mining system for detecting admissions marked as positive for several diseases: Lung Cancer, Breast Cancer, Colon Cancer, Secondary Malignant Neoplasm of Respiratory and Digestive Organs, Multiple Myeloma and Malignant Plasma Cell Neoplasms, Pneumonia, and Pulmonary Embolism. We specifically examine the effect of linking multiple data sources on text classification performance.",
    keywords = "Cancer record retrieval, Text mining, Natural Language Processing, Electronic Health Records, Radiology, Pathology",
    author = "Simon Kocbek and Lawrence Cavedon and David Martinez and Christopher Bain and {Mac Manus}, Chris and Gholamreza Haffari and Ingrid Zukerman and Karin Verspoor",
    year = "2016",
    month = "10",
    day = "11",
    doi = "10.1016/j.jbi.2016.10.008",
    language = "English",
    volume = "64",
    pages = "158--167",
    journal = "Journal of Biomedical Informatics",
    issn = "1532-0464",
    publisher = "Elsevier",

    }

    Kocbek, S, Cavedon, L, Martinez, D, Bain, C, Mac Manus, C, Haffari, G, Zukerman, I & Verspoor, K 2016, 'Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources' Journal of Biomedical Informatics, vol. 64, pp. 158-167. https://doi.org/10.1016/j.jbi.2016.10.008

    Text mining electronic hospital records to automatically classify admissions against disease : Measuring the impact of linking data sources. / Kocbek, Simon; Cavedon, Lawrence; Martinez, David; Bain, Christopher; Mac Manus, Chris; Haffari, Gholamreza; Zukerman, Ingrid; Verspoor, Karin.

    In: Journal of Biomedical Informatics, Vol. 64, 11.10.2016, p. 158-167.

    Research output: Contribution to journal › Article › Research › peer-review

    TY - JOUR

    T1 - Text mining electronic hospital records to automatically classify admissions against disease

    T2 - Measuring the impact of linking data sources

    AU - Kocbek, Simon

    AU - Cavedon, Lawrence

    AU - Martinez, David

    AU - Bain, Christopher

    AU - Mac Manus, Chris

    AU - Haffari, Gholamreza

    AU - Zukerman, Ingrid

    AU - Verspoor, Karin

    PY - 2016/10/11

    Y1 - 2016/10/11

    N2 - Text and data mining play an important role in obtaining insights from Health and Hospital Information Systems. This paper presents a text mining system for detecting admissions marked as positive for several diseases: Lung Cancer, Breast Cancer, Colon Cancer, Secondary Malignant Neoplasm of Respiratory and Digestive Organs, Multiple Myeloma and Malignant Plasma Cell Neoplasms, Pneumonia, and Pulmonary Embolism. We specifically examine the effect of linking multiple data sources on text classification performance.

    AB - Text and data mining play an important role in obtaining insights from Health and Hospital Information Systems. This paper presents a text mining system for detecting admissions marked as positive for several diseases: Lung Cancer, Breast Cancer, Colon Cancer, Secondary Malignant Neoplasm of Respiratory and Digestive Organs, Multiple Myeloma and Malignant Plasma Cell Neoplasms, Pneumonia, and Pulmonary Embolism. We specifically examine the effect of linking multiple data sources on text classification performance.

    KW - Cancer record retrieval

    KW - Text mining

    KW - Natural Language Processing

    KW - Electronic Health Records

    KW - Radiology

    KW - Pathology

    UR - http://www.scopus.com/inward/record.url?scp=84991794149&partnerID=8YFLogxK

    U2 - 10.1016/j.jbi.2016.10.008

    DO - 10.1016/j.jbi.2016.10.008

    M3 - Article

    VL - 64

    SP - 158

    EP - 167

    JO - Journal of Biomedical Informatics

    JF - Journal of Biomedical Informatics

    SN - 1532-0464

    ER -

    Kocbek S, Cavedon L, Martinez D, Bain C, Mac Manus C, Haffari G et al. Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources. Journal of Biomedical Informatics. 2016 Oct 11;64:158-167. https://doi.org/10.1016/j.jbi.2016.10.008

    Access to Document