LONDON – The first systematic review and meta-analysis of the accuracy of artificial intelligence in health care has concluded AI may be as good as clinicians in interpreting medical images, but it is hard to be sure because of the poor quality of published studies. Researchers at Birmingham University, U.K. considered 31,887 journal papers appearing between January 2012 and June 2019, of which 20,530 were screened. They found most were methodologically flawed.