AI and Diagnosis

Podcast: Download (Duration: 1:02 — 1.4MB)

Subscribe: RSS

October 22, 2019

Anchor lead: How does artificial intelligence compare with experienced docs when it comes to diagnosis? Elizabeth Tracey reports

Artificial intelligence, where computers are taught to interpret images, are able to make an accurate diagnosis of a disease with about the same accuracy as experienced clinicians, a recent Lancet study found. Paul Rothman, dean of the Johns Hopkins School of Medicine, describes results from different studies.

Rothman: Other studies have demonstrated that if you take experienced clinicians and AI you get much better accuracy than either one by itself so it’s not like AI is going to supplant physicians today but I think the combination in using AI as an aid has real power.  :18

Rothman says the field is in its infancy.

Rothman: With the advent of artificial intelligence and machine learning, we think that computers can help us analyze data and better take care of our patients. I would say it’s in the early days of AI in medicine. I think it’s going to be in the long term very important but it’s just at its beginning right now.  :19

At Johns Hopkins, I’m Elizabeth Tracey.