Empirical assessment of bias in machine learning diagnostic test accuracy studies.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 32548642

Abstract

OBJECTIVE: Machine learning (ML) diagnostic tools have significant potential to improve health care. However, methodological pitfalls may affect diagnostic test accuracy studies used to appraise such tools. We aimed to evaluate the prevalence and reporting of design characteristics within the literature. Further, we sought to empirically assess whether design features may be associated with different estimates of diagnostic accuracy.

Authors

  • Ryan J Crowley
    Meta-Research Innovation Center at Stanford, Stanford University, Stanford, California, USA.
  • Yuan Jin Tan
    Meta-Research Innovation Center at Stanford, Stanford University, Stanford, California, USA.
  • John P A Ioannidis
    Stanford Prevention Research Center, Department of Medicine, Stanford University, Stanford, California.

Keywords

External Resources

Popular Topics
Recent Journals