Clinical Research

‘Low-trust’ providers inadvertently increase pain in patients undergoing diagnostic testing

The effect shows up on functional MRI as increased brain activity in regions involved in pain, emotion and attention—not only during the procedure but also afterward, when patients remember the experience and score its discomfort level.

An overview of artificial intelligence (AI) in radiology with Keith Dreyer with the ACR. Images shows a COVID-19 lung CT scan reconstruction from Siemens Healthineers. #AI #radAI #ACR

AI speeds, improves chest X-ray interpretations

Six radiologists interpreting around 500 chest radiographs with an assist from AI bested unaided radiologists in measures of efficiency and/or accuracy in a new comparative performance study.    

Christine Albert, MD, MPH, cardiology chair for the Smidt Heart Institute at Cedars-Sinai Medical Center

Rethinking arrhythmias: Women may face a higher AFib risk than men

New research, published in JAMA Cardiology, challenges the common belief that AFib is more likely to develop among men than women. The key problem, it seems, is that prior research teams did not understand the significance of certain risk factors.

Pediatric radiologists skillfully read emergency breast ultrasound—but patients may shrug off discharge instructions

For this reason, these patients may need pointed guidance upon ED discharge lest cancers go undetected in early stages.  

Thumbnail

5 imaging modalities have changed the war on cancer over the past 50 years. How many can you name?

Two branch chiefs with the cancer imaging program at NIH’s National Cancer Institute have produced a written commemoration to mark the golden anniversary of 1971’s National Cancer Act.

Jianyi "Jay" Zhang, MD, PhD, is leading research on growing new heart muscle cells

Researchers receive $11.2M to study how the heart recovers from significant damage

The National Heart, Lung and Blood Institute, part of the National Institutes of Health, awarded the funds to three research teams. 

AI research published without code, data, documentation interesting to readers but unhelpful to science: RSNA pubs review

Over the five-year period ending last December 31, only a third of 218 scientific articles on AI in four popular radiology journals shared the researchers’ code.