AI technology expands capabilities—and what that means for radiology

Radiologists aren't going to be replaced by computers tomorrow, but Denver-area radiologist and Forbes contributor Paul Hsieh acknowledges the rise of deep learning AI technology has opened the door to medical work previously thought to be out of reach of automation.

"If you asked me 10 years ago, I would have said, 'No way!' But if you ask me today, my answer would be more hesitant, 'Not yet—but perhaps someday soon.'" he wrote. "For example, deep learning algorithms have been able to diagnose the presence or absence of tuberculosis (TB) in chest x-ray images with astonishing accuracy."

The promise of deep learning extends beyond radiology, too. Researchers from Google trained AI to detect breast cancer on microscopic slides of lymph node tissue, identifying cancer much more accurately than human pathologists.

However, the most interesting use of deep learning technology is uncovering associations yet undiscovered by human scientists. For example, a Stanford University study pitted the predictive value of American College of Cardiology (ACC)/American Heart Association (AHA) risk factors for cardiovascular disease against the predictive value of several artificial intelligence algorithms.

All four AI methods performed significantly better than the ACC/AHA guidelines,” wrote Science contributor Matthew Hutson. “In the test sample of about 83,000 records, that amounts to 355 additional patients whose lives could have been saved.”

Read the full article at Forbes by following the link below:

As a Senior Writer for TriMed Media Group, Will covers radiology practice improvement, policy, and finance. He lives in Chicago and holds a bachelor’s degree in Life Science Communication and Global Health from the University of Wisconsin-Madison. He previously worked as a media specialist for the UW School of Medicine and Public Health. Outside of work you might see him at one of the many live music venues in Chicago or walking his dog Holly around Lakeview.

Around the web

The ACR hopes these changes, including the addition of diagnostic performance feedback, will help reduce the number of patients with incidental nodules lost to follow-up each year.

And it can do so with almost 100% accuracy as a first reader, according to a new large-scale analysis.

The patient, who was being cared for in the ICU, was not accompanied or monitored by nursing staff during his exam, despite being sedated.