Can we accurately classify schizophrenia patients from healthy controls using magnetic resonance imaging and machine learning? A multi-method and multi-dataset study.

Machine learning is a powerful tool that has previously been used to classify schizophrenia (SZ) patients from healthy controls (HC) using magnetic resonance images. Each study, however, uses different datasets, classification algorithms, and validation techniques. Here, we perform a critical apprai...

Descripción completa

Detalles Bibliográficos
Publicado en:Schizophrenia Research Vol. 214; pp. 3 - 11
Autores principales: Winterburn, Julie L., Voineskos, Aristotle N., Devenyi, Gabriel A., Plitman, Eric, de la Fuente-Sandoval, Camilo, Bhagwat, Nikhil, Graff-Guerrero, Ariel, Knight, Jo, Chakravarty, M. Mallar
Formato: research Journal Article
Publicado: Elsevier B.V. Dec2019
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=141109794&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 141109794
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        09209964
        3PT
      jtl: Schizophrenia Research
      issn: 09209964
      maglogo: N
    pubinfo:
      dt: Dec2019
      vid: 214
      pid: 1004
      pub: Elsevier B.V.
    artinfo:
      ui:
        141109794
        141109794
        NLM29274736
        141109794
        10.1016/j.schres.2017.11.038
        NLM29274736
        141109794
      ppf: 3
      ppct: 8
      formats:
      tig:
        atl: Can we accurately classify schizophrenia patients from healthy controls using magnetic resonance imaging and machine learning? A multi-method and multi-dataset study.
      aug:
        au:
          Winterburn, Julie L.
          Voineskos, Aristotle N.
          Devenyi, Gabriel A.
          Plitman, Eric
          de la Fuente-Sandoval, Camilo
          Bhagwat, Nikhil
          Graff-Guerrero, Ariel
          Knight, Jo
          Chakravarty, M. Mallar
        affil: Computational Brain Anatomy Laboratory, Douglas Mental Health Institute, McGill University, Montreal, Quebec, Canada
      sug:
        subj:
          Magnetic Resonance Imaging Methods
          Brain
          Schizophrenia Classification
          Schizophrenia
          Schizophrenia Pathology
          Human
          Male
          Data Collection
          Image Interpretation, Computer Assisted Methods
          Adult
          Brain Pathology
          Body Weights and Measures
          Female
          Validation Studies
          Comparative Studies
          Evaluation Research
          Multicenter Studies
          Scales
          Adult: 19-44 years
          Male
          Female
      ab: Machine learning is a powerful tool that has previously been used to classify schizophrenia (SZ) patients from healthy controls (HC) using magnetic resonance images. Each study, however, uses different datasets, classification algorithms, and validation techniques. Here, we perform a critical appraisal of the accuracy of machine learning methodologies used in SZ/HC classifications studies by comparing three machine learning algorithms (logistic regression [LR], support vector machines [SVMs], and linear discriminant analysis [LDA]) on three independent datasets (435 subjects total) using two tissue density estimates and cortical thickness (CT). Performance is assessed using 10-fold cross-validation, as well as a held-out validation set. Classification using CT outperformed tissue densities, but there was no clear effect of dataset. LR, SVMs, and LDA each yielded the highest accuracies for a different feature set and validation paradigm, but most accuracies were between 55 and 70%, well below previously reported values. The highest accuracy achieved was 73.5% using CT data and an SVM. Taken together, these results illustrate some of the obstacles to constructing effective disease classifiers, and suggest that tissue densities and CT may not be sufficiently sensitive for SZ/HC classification given current available methodologies and sample sizes.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N