Uncertainty, Evidence, and the Integration of Machine Learning into Medical Practice.

In light of recent advances in machine learning for medical applications, the automation of medical diagnostics is imminent. That said, before machine learning algorithms find their way into clinical practice, various problems at the epistemic level need to be overcome. In this paper, we discuss dif...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Medicine & Philosophy Vol. 48; no. 1; pp. 84 - 98
Autores principales: Grote, Thomas, Berens, Philipp
Formato: Artículo
Publicado: Oxford University Press / USA Feb2023
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=161964068&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 161964068
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        03605310
        MPS
      jtl: Journal of Medicine & Philosophy
      issn: 03605310
      maglogo: N
    pubinfo:
      dt: Feb2023
      vid: 48
      iid: 1
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        161964068
        10.1093/jmp/jhac034
      ppf: 84
      ppct: 14
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 256KB
      tig:
        atl: Uncertainty, Evidence, and the Integration of Machine Learning into Medical Practice.
      aug:
        au:
          Grote, Thomas
          Berens, Philipp
        affil: University of Tübingen , Tübingen , Germany
      su:
        Deep learning
        Machine learning
        Medical practice
        Bored piles
        Trust
      sug:
        subj:
          Deep learning
          Machine learning
          Medical practice
          Bored piles
          Trust
      keyword:
        black box problem
        evidence
        machine learning
        medical diagnosis
        uncertainty
      ab: In light of recent advances in machine learning for medical applications, the automation of medical diagnostics is imminent. That said, before machine learning algorithms find their way into clinical practice, various problems at the epistemic level need to be overcome. In this paper, we discuss different sources of uncertainty arising for clinicians trying to evaluate the trustworthiness of algorithmic evidence when making diagnostic judgments. Thereby, we examine many of the limitations of current machine learning algorithms (with deep learning in particular) and highlight their relevance for medical diagnostics. Among the problems we inspect are the theoretical foundations of deep learning (which are not yet adequately understood), the opacity of algorithmic decisions, and the vulnerabilities of machine learning models, as well as concerns regarding the quality of medical data used to train the models. Building on this, we discuss different desiderata for an uncertainty amelioration strategy that ensures that the integration of machine learning into clinical settings proves to be medically beneficial in a meaningful way.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: © 2019 Journal of Medicine and Philosophy Inc..
      item: Journal of Medicine & Philosophy
      holder: Oxford University Press / USA
      dt:
        @attributes:
          year: 2023
    holdings:
      @attributes:
        islocal: N