Op-ed: How machines may transform health care 'beyond recognition'

Providers now need to start preparing for "machine learning" medicine, two professors write in a New England Journal of Medicine perspective. Ziad Obermeyer, an assistant professor at Harvard Medical School, and Ezekiel Emanuel, chair of the Department of Medical Ethics and Health Policy at University of Pennsylvania, write that computers eventually will be more effective than human providers at making a range of health care decisions--from determining the most cost-effective surgical supplies to deciding which tests a patient can skip. For example, they predict computer programs will be able to analyze radiographs for anomalies at a pixel level, a much more precise level of detail than the human eye is capable of detecting. "We can point this very powerful tool at a medical problem and say, 'I'm going to show you a bunch of people who had heart attacks, and a bunch who didn't. Go learn how to tell them apart,'" Obermeyer says in an interview with STAT News.