Peering Into the Black Box of Artificial Intelligence: Evaluation Metrics of Machine Learning Methods.

Journal: AJR. American journal of roentgenology
Published Date:

Abstract

OBJECTIVE: Machine learning (ML) and artificial intelligence (AI) are rapidly becoming the most talked about and controversial topics in radiology and medicine. Over the past few years, the numbers of ML- or AI-focused studies in the literature have increased almost exponentially, and ML has become a hot topic at academic and industry conferences. However, despite the increased awareness of ML as a tool, many medical professionals have a poor understanding of how ML works and how to critically appraise studies and tools that are presented to us. Thus, we present a brief overview of ML, explain the metrics used in ML and how to interpret them, and explain some of the technical jargon associated with the field so that readers with a medical background and basic knowledge of statistics can feel more comfortable when examining ML applications.

Authors

  • Guy S Handelman
    1 Department of Radiology, Belfast City Hospital, 51 Lisburn Rd, Belfast, Antrim BT9 7AB, UK.
  • Hong Kuan Kok
    Interventional Radiology Service, Department of Radiology, Beaumont Hospital, Dublin, Ireland.
  • Ronil V Chandra
    5 Interventional Neuroradiology Service, Monash Imaging, Monash Health, Clayton, Australia.
  • Amir H Razavi
    7 School of Information Technology and Engineering, University of Ottawa, Ottawa, ON, Canada.
  • Shiwei Huang
    9 The Australian National University Medical School, Garran, Australia.
  • Mark Brooks
    5 Interventional Neuroradiology Service, Monash Imaging, Monash Health, Clayton, Australia.
  • Michael J Lee
    2 Royal College of Surgeons in Ireland, Dublin, Ireland.
  • Hamed Asadi
    Neurointerventional Service, Department of Radiology, Beaumont Hospital, Dublin, Ireland; School of Medicine, Faculty of Health, Deakin University, Waurn Ponds, Australia. Electronic address: asadi.hamed@gmail.com.