[Skip to Navigation]
November 12, 2019

Evaluating Machine Learning Articles

Author Affiliations
  • 1Harvard University, Boston, Massachusetts
  • 2Massachusetts General Hospital, Boston
JAMA. 2019;322(18):1777-1779. doi:10.1001/jama.2019.17304

In this issue of JAMA, Liu and colleagues1 provide a users’ guide to reading clinical machine learning articles. Beyond a synopsis of selected concepts in modern machine learning, the authors elaborate step-by-step guidance for physicians seeking to evaluate this evidence with a critical eye. In an era when readers are bombarded with artificial intelligence in everyday life, from credit card fraud warnings and smartphones that anticipate their needs to life-like videos of people who do not actually exist, the sanity check provided by this article is most welcome.