Machine learning in medicine: Medical droids, tricorders, and a computer named Hal 9000.

Journal: Nephrologie & therapeutique
Published Date:

Abstract

The usage of artificial intelligence to evaluate histological images was recently explored in many different areas of pathology. Studies focusing on nephropathology demonstrated that algorithms could be trained to identify various structures of the kidney, like glomeruli and interstitium, as well as performing a classification task just as good as highly experienced pathologists. It is conceivable that further development of digitalized pathology in combination with all opportunities that artificial intelligence and machine learning have to offer, will rapidly change the work of the clinical pathologist in a substantial way.

Authors

  • Ingeborg M Bajema
    Department of Pathology, L1Q, Leiden University Medical Center, PO Box 9600, 2300 RC Leiden, The Netherlands. Electronic address: i.bajema@lumc.nl.