Validating, Implementing, and Monitoring Machine Learning Solutions in the Clinical Laboratory Safely and Effectively.

Journal: Clinical chemistry
Published Date:

Abstract

BACKGROUND: Machine learning solutions offer tremendous promise for improving clinical and laboratory operations in pathology. Proof-of-concept descriptions of these approaches have become commonplace in laboratory medicine literature, but only a scant few of these have been implemented within clinical laboratories, owing to the often substantial barriers in validating, implementing, and monitoring these applications in practice. This mini-review aims to highlight the key considerations in each of these steps.

Authors

  • Nicholas C Spies
    McDonnell Genome Institute, Washington University School of Medicine, St. Louis, Missouri, USA.
  • Christopher W Farnsworth
    Department of Pathology, Washington University in St.Louis School of Medicine, St. Louis, MO, United States.
  • Sarah Wheeler
    Department of Pathology, University of Pittsburgh School of Medicine and UPMC, Pittsburgh, PA, United States.
  • Christopher R McCudden
    Department of Pathology and Laboratory Medicine, Division of Biochemistry, Eastern Ontario Regional Laboratory Association, Ottawa Hospital, University of Ottawa, Ottawa, Canada.