Health Imaging | Homepage

artificial intelligence healthcare industry digest

Are LLMs ready for radiology? Research reveals how chatbots' performance has evolved over time

Large language models have shown great potential in medical imaging, but their success has been hindered by their wavering effectiveness. Now, nearly three years after ChatGPT's release, experts are sharing new insights.

Dana Smetherman, MD, MPH, MBA, FACR, chief executive officer of the American College of Radiology, explains how the consolidation of radiology practices into larger corporate entities now makes up more than 50% of how radiologists are employed. This led to changes in how ACR accredits sites.

ACR changing its accreditation process in response to corporate consolidation

CEO Dana Smetherman, MD, MPH, MBA, explains how the consolidation of radiology practices has shifted how the college thinks about its processes.

Repeat imaging rates higher when scans are interpreted by nurse practitioners, physician assistants

The finding is based on an analysis of nearly 1.4 million office-based imaging claims, conducted by the Harvey L. Neiman Health Policy Institute.

prior authorization claim deny denial insurance insurer payer Medicare Advantage

Members of Congress condemn Medicare model targeting ‘wasteful’ interventional radiology services

“It is not an exaggeration to say that the requirement of prior authorization for traditional Medicare services will kill seniors,” says Rep. Mark Pocan, D-Wis.

Referrers frequently failing to recommend patients for key interventional radiology procedure

An analysis of nearly 272,000 uterine fibroid healthcare encounters shows that only about 4% of women underwent uterine fibroid embolization, a minimally invasive IR treatment option.

AI model reduces false positives on lung cancer CT scans

AI model nearly halves false positive rates for lung cancer CT screenings

Reducing false positives could decrease the frequency of unnecessary procedures, lower the associated costs and also ease patient anxiety concerning CT results.

Around the web

Cardiovascular Business

AI turns mammograms into CVD risk assessments—no outside data required

Thanks to AI, clinicians can use mammograms to do a lot more than identify signs of breast cancer. Researchers explored data from nearly 50,000 patients, presenting their findings in Heart.