Enhancing rule-based text classification of neurosurgical notes using filtered feature weight vectors

Sedigheh Khademi , Pari Delir Haghighi, Frada Burstein, Christopher Palmer

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    1 Citation (Scopus)


    Clinicians need to record clinical encounters in written or spoken language, not only for its work-flow naturalness but also for its expressivity, precision, and capacity to convey all required information, which codified structured data is incapable of. Therefore, the structured data which is required for aggregation and analysis must be obtained from clinical text as a later step. Specialised areas of medicine use their own clinical language and clinical coding systems, resulting in unique challenges for the extraction process. Rule-based information extraction techniques have been used effectively in commercial systems and are favoured because they are easily understood and controlled. However, there is promising research into the use of machine learning techniques for extracting information, and this research explores the effectiveness of a hybrid rule-based and machine learning-based audit coding system developed for the neurosurgical department of a major trauma hospital.

    Original languageEnglish
    Title of host publicationProceedings of the 27th Australasian Conference on Information Systems (ACIS 2016)
    EditorsJulie Fisher, Walter Fernandez
    Place of PublicationWollongong NSW Australia
    PublisherUniversity of Wollongong
    Number of pages11
    ISBN (Electronic)9781741282672
    Publication statusPublished - 2016
    EventAustralasian Conference on Information Systems 2016 - University of Wollongong, Wollongong, Australia
    Duration: 5 Dec 20167 Dec 2016
    Conference number: 27th
    http://acis.aaisnet.org/proceedings/2016.zip (Proceedings)

    Publication series

    NameProceedings of the 27th Australasian Conference on Information Systems, ACIS 2016


    ConferenceAustralasian Conference on Information Systems 2016
    Abbreviated titleACIS 2016
    OtherInformation systems (IS) have become an unrecognised commodity – everybody uses them, yet as IS researchers and practitioners we seem to need to explain time and again what we do, what value we provide, and keep justifying our existence.

    ACIS 2016 provides the opportunity to do just that and offers the opportunity how we, as the IS community, take up that challenge.
    Internet address


    • Audit coding
    • Information extraction
    • Machine learning
    • Neurosurgery
    • Rule-based expert systems

    Cite this