radRounds Radiology Network

Connecting Radiology | Enabling collaboration and professional development

Machine learning has turned data science on its head. Now that we can teach computers to solve problems, programmers no longer need to. This advancement has revolutionized the way we approach and use technology. We’ve already seen the positive impact of machine learning in voice-automated apps like Amazon’s Alexa and Microsoft’s Cortana. We’re now poised to witness the evolution of machine learning in medical technology.


Some experts posit that machine learning is on the brink of replacing the responsibilities of radiologists. According to Ziad Obermeyer, MD, Assistant Professor at both Harvard Medical School and Brigham & Women’s Hospital, and Ezekiel J. Emanuel, MD, the Chair of the Department of Medical Ethics and Health Policy at the University of Pennsylvania, describe their predictions for the profession in an article for The New England Journal of Medicine. 


Massive imaging data sets, combined with recent advances in computer vision, will drive rapid improvements in performance, and machine accuracy will soon exceed that of humans,” they write. “Indeed, radiology is already partway there: Algorithms can replace a second radiologist reading mammograms and will soon exceed human accuracy.”


Notable radiologist Nick Bryan, MD, of Penn Medicine concurs with his belief that machine learning is set to diagnose diseases like Alzehimer’s and detect new patterns in schizophrenia. In an op-ed for the Radiological Society of North America, he claims that modern imaging technology “is creating image data sets that exceed human pattern recognition capabilities.”


Other experts don’t believe machine learning will put radiologists out of work. Take for example, Mayo Clinic researcher Bradley J. Erickson, MD, PhD, who thinks the technology will simply enhance their diagnosing capabilities and treatment strategy. “Radiologists would be able to focus much more on patient interaction and invasive procedures and let some of the more routine imaging be handled by computers," he told a Society for Imaging Informatics in Medicine webinar.


Only time will tell if medical technology will ever be sophisticated enough to put radiologists on the extinction watch list. For now, we couldn’t live without their service. 


Views: 1409


You need to be a member of radRounds Radiology Network to add comments!

Join radRounds Radiology Network

Sponsor Ad

© 2019   Created by radRounds Radiology Network.   Powered by

Badges  |  Report an Issue  |  Terms of Service