Key concepts, common pitfalls, and best practices in artificial intelligence and machine learning: focus on radiomics.

Artificial intelligence (AI) and machine learning (ML) are increasingly used in radiology research to deal with large and complex imaging data sets. Nowadays, ML tools have become easily accessible to anyone. Such a low threshold to accessibility might lead to inappropriate usage and misinterpretati...

Descripción completa

Detalles Bibliográficos
Publicado en:Diagnostic & Interventional Radiology Vol. 28; no. 5; pp. 450 - 463
Autor principal: Koçak, Burak
Formato: diagnostic images research tables/charts Journal Article
Publicado: Galenos Yayinevi Tic. LTD. STI Sep2022
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=159741424&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 159741424
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        13053825
        39NM
      jtl: Diagnostic & Interventional Radiology
      issn: 13053825
      maglogo: N
    pubinfo:
      dt: Sep2022
      vid: 28
      iid: 5
      pid: 28155
      pub: Galenos Yayinevi Tic. LTD. STI
    artinfo:
      ui:
        159741424
        159741424
        NLM36218149
        159741424
        10.5152/dir.2022.211297
        NLM36218149
        159741424
      ppf: 450
      ppct: 13
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Key concepts, common pitfalls, and best practices in artificial intelligence and machine learning: focus on radiomics.
      aug:
        au: Koçak, Burak
        affil: Department of Radiology, Basaksehir Cam and Sakura City Hospital, Basaksehir, İstanbul, Turkey
      sug:
        subj:
          Specialties, Medical Methods
          Artificial Intelligence
          Human
          Reproducibility of Results
      ab: Artificial intelligence (AI) and machine learning (ML) are increasingly used in radiology research to deal with large and complex imaging data sets. Nowadays, ML tools have become easily accessible to anyone. Such a low threshold to accessibility might lead to inappropriate usage and misinterpretation, without a clear intention. Therefore, ensuring methodological rigor is of paramount importance. Getting closer to the real-world clinical implementation of AI, a basic understanding of the main concepts should be a must for every radiology professional. In this respect, simplified explanations of the key concepts along with pitfalls and recommendations would be helpful for general radiology community to develop and improve their AI mindset. In this work, twenty-two key issues are reviewed within three categories: pre-modeling, modeling, and post-modeling. Firstly, the concept is shortly defined for each issue. Then, related common pitfalls and best practices are provided. Specifically, the issues included in this paper were validity of scientific question, unrepresentative samples, sample size, missing data, quality of reference standard, batch effect, reliability of features, feature scaling, multi-collinearity, class imbalance, data and target leakage, high-dimensional data, optimization, overfitting, generalization, performance metrics, clinical utility, comparison with conventional statistical and clinical methods, interpretability and explainability, randomness, transparent reporting, and sharing data.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N