Imbalanced target prediction with pattern discovery on clinical data repositories.

Background: Clinical data repositories (CDR) have great potential to improve outcome prediction and risk modeling. However, most clinical studies require careful study design, dedicated data collection efforts, and sophisticated modeling techniques before a hypothesis can be tested. We aim to bridge...

Descripción completa

Detalles Bibliográficos
Publicado en:BMC Medical Informatics & Decision Making Vol. 17; pp. 1 - 13
Autores principales: Tak-Ming Chan, Yuxi Li, Choo-Chiap Chiau, Jane Zhu, Jie Jiang, Yong Huo, Chan, Tak-Ming, Li, Yuxi, Chiau, Choo-Chiap, Zhu, Jane, Jiang, Jie, Huo, Yong
Formato: equations & formulas research tables/charts Journal Article
Publicado: BioMed Central 4/20/2017
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=122656489&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 122656489
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        14726947
        1CI0
      jtl: BMC Medical Informatics & Decision Making
      issn: 14726947
      maglogo: N
    pubinfo:
      dt: 4/20/2017
      vid: 17
      pid: 24147
      pub: BioMed Central
    artinfo:
      ui:
        122656489
        122656489
        NLM28427384
        122656489
        10.1186/s12911-017-0443-3
        NLM28427384
        122656489
      ppf: 1
      ppct: 12
      formats:
      tig:
        atl: Imbalanced target prediction with pattern discovery on clinical data repositories.
      aug:
        au:
          Tak-Ming Chan
          Yuxi Li
          Choo-Chiap Chiau
          Jane Zhu
          Jie Jiang
          Yong Huo
          Chan, Tak-Ming
          Li, Yuxi
          Chiau, Choo-Chiap
          Zhu, Jane
          Jiang, Jie
          Huo, Yong
        affil: Philips Research China - Health Systems, China, Philips Innovation Campus Shanghai, No. 1 Building, 10, Lane 888, Tian Lin Road, Shanghai 200233, China
      sug:
        subj:
          Data Mining Methods
          Computer Simulation
          Information Science Methods
          Databases Administration
          Algorithms
          Health Information Systems Administration
          Forecasting
          Human
      ab: Background: Clinical data repositories (CDR) have great potential to improve outcome prediction and risk modeling. However, most clinical studies require careful study design, dedicated data collection efforts, and sophisticated modeling techniques before a hypothesis can be tested. We aim to bridge this gap, so that clinical domain users can perform first-hand prediction on existing repository data without complicated handling, and obtain insightful patterns of imbalanced targets for a formal study before it is conducted. We specifically target for interpretability for domain users where the model can be conveniently explained and applied in clinical practice.Methods: We propose an interpretable pattern model which is noise (missing) tolerant for practice data. To address the challenge of imbalanced targets of interest in clinical research, e.g., deaths less than a few percent, the geometric mean of sensitivity and specificity (G-mean) optimization criterion is employed, with which a simple but effective heuristic algorithm is developed.Results: We compared pattern discovery to clinically interpretable methods on two retrospective clinical datasets. They contain 14.9% deaths in 1 year in the thoracic dataset and 9.1% deaths in the cardiac dataset, respectively. In spite of the imbalance challenge shown on other methods, pattern discovery consistently shows competitive cross-validated prediction performance. Compared to logistic regression, Naïve Bayes, and decision tree, pattern discovery achieves statistically significant (p-values < 0.01, Wilcoxon signed rank test) favorable averaged testing G-means and F1-scores (harmonic mean of precision and sensitivity). Without requiring sophisticated technical processing of data and tweaking, the prediction performance of pattern discovery is consistently comparable to the best achievable performance.Conclusions: Pattern discovery has demonstrated to be robust and valuable for target prediction on existing clinical data repositories with imbalance and noise. The prediction results and interpretable patterns can provide insights in an agile and inexpensive way for the potential formal studies.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N