Performance metrics for machine learning solutions in laboratory medicine.

Machine learning–based solutions to laboratory medicine problems have become commonplace in literature, but real-world implementations remain rare, in no small part because of the substantial investment required to incorporate such solutions into routine clinical care. A crucial step in advancing a...

Descripción completa

Detalles Bibliográficos
Publicado en:Laboratory Medicine Vol. 56; no. 6; pp. 597 - 608
Autores principales: Spies, Nicholas C, Ng, David P
Formato: equations & formulas review tables/charts Journal Article
Publicado: Oxford University Press / USA Nov2025
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=189866426&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 189866426
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00075027
        4CY
      jtl: Laboratory Medicine
      issn: 00075027
      maglogo: N
    pubinfo:
      dt: Nov2025
      vid: 56
      iid: 6
      pid: 10398
      pub: Oxford University Press / USA
    artinfo:
      ui:
        189866426
        189866426
        189866426
        10.1093/labmed/lmaf013
        189866426
      ppf: 597
      ppct: 11
      formats:
      tig:
        atl: Performance metrics for machine learning solutions in laboratory medicine.
      aug:
        au:
          Spies, Nicholas C
          Ng, David P
        affil: Department of Pathology, University of Utah, Salt Lake City, UT, United States
      sug:
        subj:
          Machine Learning
          Clinical Laboratories
          Problem Solving
          Medical Practice
          Sensitivity and Specificity
          Predictive Value of Tests
          Diagnosis, Laboratory
          Diagnosis, Computer Assisted
          Artificial Intelligence
          Diagnostic Errors
          Classification Algorithms
      ab: Machine learning–based solutions to laboratory medicine problems have become commonplace in literature, but real-world implementations remain rare, in no small part because of the substantial investment required to incorporate such solutions into routine clinical care. A crucial step in advancing a machine learning solution from proof of concept into clinical application is a robust and comprehensive evaluation of its performance. In this review, we discuss the common methods, best practices, and potential pitfalls in evaluating machine learning–based solutions to clinical laboratory problems.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        review
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N