AI opportunistic screening may have tremendous potential to help patients, ACR CEO says

 

A technology trend that is gaining interest in radiology is the use of artificial intelligence algorithms to opportunistically screen patients for diseases who are getting an unrelated medical imaging exam. The AI works in the background and only alerts radiologists if there is a suspected finding. This has the potential to catch diseases in very early stages when it is easier to treat or prevent progression.

Radiology Business spoke with American College of Radiology CEO Dana H. Smetherman, MD, MBA, about this trend and why radiology practices should be paying attention. 

“I do think this idea of opportunistic, or serendipitous screening, is a very interesting one, although it's more screening for preclinical disease, but it's a potentially powerful tool,” Smetherman explained. 

She said a CT of the chest, abdomen or pelvis contains large amounts of data about a patient. But imaging tests are usually performed to answer a specific clinical question, and much of the data available is never really looked at. That enormous amount of data can be processed by AI to do a variety of screening tasks.

"There are already tools that can detect osteoporosis based on the bony structures that are on those imaging studies. You could put an entire population through there and predict perhaps who might be at risk for having a hip fracture down the road. So yes, tremendous potential to help patients, help them avoid significant disease in the future," Smetherman said.

AI can be used to look for incidental findings to act as a second set of eyes for a radiologist, but opportunistic screenings may be able to go beyond just looking for incidental lung nodules or lymphadenopathy. AI can see complex patterns in the imaging data and subtle signs in imaging that the human eye can miss. Maybe a human radiologist can perceive some of the small details, but they do not have an easy way to quantify it, so it is not extremely useful, she said. But AI can now perform these complex and precise quantifications. This area includes radiomics AI, which can determine a patient's risks factors and enable much earlier disease detection, long before a patient develops symptoms. 

"I think there is tremendous population health potential there. If you could take all the mammograms that are done and look at the vascular calcifications that are in arteries across an entire practice's mammograms, and if that were able to predict which of those women might be at risk for significant vascular disease, heart attacks and strokes in five, 10 or 15 years in the future, that would be amazing. And that is data that may already be there and we just need to study it," Smetherman explained.

From a business prospective, opportunistic screening algorithms will likely offer health systems a new way to not only better serve patients by catching diseases earlier when they are easier to treat or prevent, but also serve as an entry point for additional testing and treatments without large amounts of time or investment to create new screening programs.

Dave Fornell is a digital editor with Cardiovascular Business and Radiology Business magazines. He has been covering healthcare for more than 16 years.

Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: dfornell@innovatehealthcare.com

Around the web

After reviewing years of data from its clinic, one institution discovered that issues with implant data integrity frequently put patients at risk. 

Prior to the final proposal’s release, the American College of Radiology reached out to CMS to offer its recommendations on payment rates for five out of the six the new codes.

“Before these CPT codes there was no real acknowledgment of the additional burden borne by the providers who accepted these patients."

Trimed Popup
Trimed Popup