Curtin University Homepage
  • Library
  • Help
    • Admin

    espace - Curtin’s institutional repository

    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item

    A framework for feature extraction from hospital medical data with applications in risk prediction

    232902_232902.pdf (1.021Mb)
    Access Status
    Open access
    Authors
    Tran, The Truyen
    Luo, W.
    Phung, D.
    Gupta, S.
    Rana, S.
    Kennedy, R.
    Larkins, A.
    Venkatesh, S.
    Date
    2014
    Type
    Journal Article
    
    Metadata
    Show full item record
    Citation
    Tran, T.T. and Luo, W. and Phung, D. and Gupta, S. and Rana, S. and Kennedy, R. and Larkins, A. et al. 2014. A framework for feature extraction from hospital medical data with applications in risk prediction. BMC Bioinformatics. 15 (1).
    Source Title
    BMC Bioinformatics
    DOI
    10.1186/s12859-014-0425-8
    School
    Multi-Sensor Proc & Content Analysis Institute
    Remarks

    This open access article is distributed under the Creative Commons license http://creativecommons.org/licenses/by/4.0/

    URI
    http://hdl.handle.net/20.500.11937/39426
    Collection
    • Curtin Research Publications
    Abstract

    Background: Feature engineering is a time consuming component of predictive modeling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities. Results: Hospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12 months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlapping data-collection periods. For unplanned readmissions, auto-extracted feature set using socio-demographic information and medical records, outperformed baselines derived from the socio-demographic information and Elixhauser comorbidities, over 20 settings (5 prediction horizons over 4 diseases). In particular over 30-day prediction, the AUCs are: COPD-baseline: 0.60 (95% CI: 0.57, 0.63), auto-extracted: 0.67 (0.64, 0.70); diabetes-baseline: 0.60 (0.58, 0.63), auto-extracted: 0.67 (0.64, 0.69); mental disorders-baseline: 0.57 (0.54, 0.60), auto-extracted: 0.69 (0.64,0.70); pneumonia-baseline: 0.61 (0.59, 0.63), auto-extracted: 0.70 (0.67, 0.72). Conclusions: The advantages of auto-extracted standard features from complex medical records, in a disease and task agnostic manner were demonstrated. Auto-extracted features have good predictive power over multiple time horizons. Such feature sets have potential to form the foundation of complex automated analytic tasks.

    Related items

    Showing items related by title, author, creator and subject.

    • Burden of disease and benefits of exercise in fixed airway obstruction asthma
      Turner, Sian Elizabeth (2009)
      Background and research questions. The characterization of chronic persistent asthma in an older adult population is not well defined. This is due to the difficulties in separating the diagnosis of asthma from that of ...
    • The role of functional, radiological and self-reported measures in predicting clinical outcome in spondylotic cervical radiculopathy
      Agarwal, Shabnam (2011)
      BackgroundCervical radiculopathy (CR) results in significant disability and pain and is commonly treated conservatively with satisfactory clinical outcomes. However, a considerable number of patients require surgery to ...
    • Medication incidents in a private hospital : frequency, type, causes and outcomes
      McKnight, David (2011)
      Background: Medication Safety has become a major health issue in Australia and internationally. Medication use is a part of most people lives with around seven in ten Australians and nine in ten older Australians having ...
    Advanced search

    Browse

    Communities & CollectionsIssue DateAuthorTitleSubjectDocument TypeThis CollectionIssue DateAuthorTitleSubjectDocument Type

    My Account

    Admin

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Follow Curtin

    • 
    • 
    • 
    • 
    • 

    CRICOS Provider Code: 00301JABN: 99 143 842 569TEQSA: PRV12158

    Copyright | Disclaimer | Privacy statement | Accessibility

    Curtin would like to pay respect to the Aboriginal and Torres Strait Islander members of our community by acknowledging the traditional owners of the land on which the Perth campus is located, the Whadjuk people of the Nyungar Nation; and on our Kalgoorlie campus, the Wongutha people of the North-Eastern Goldfields.