Not only can different lung diseases look much the same in chest imaging, but distinct diagnoses may present widely dissimilar image patterns in the same patient at the same timepoint, too.
Those are just two of several high hurdles AI would have to consistently surmount before earning any shot at all of replacing radiologists subspecialized in pulmonary care.
Radiologist Eduardo Mortani Barbosa Jr., MD, of the University of Pennsylvania’s Perelman School of Medicine makes the point in an interview published online Sept. 16 in Pulmonology Advisor.
“[I]t is unlikely that AI systems that rely solely on imaging will replace the integrative reasoning and judgment of an astute physician, at least in the foreseeable future,” Barbosa says. “The integration of knowledge and different sources of information, combined with longitudinal assessment of patient data over time, will remain crucial for accurate diagnosis and optimal patient management.”
Writer Tori Rodriguez interviewed Barbosa together with Luciano Prevedello, MD, MPH, of The Ohio State University.
“The field [of radiological AI] is evolving quite rapidly, and many applications are receiving [FDA] approval and making their way into the clinical environment,” says Prevedello, whose areas of expertise beyond traditional radiology include medical informatics and augmented intelligence. “These tools are showing promising results and will likely have an important role in assisting us to continue to provide better care to our patients.”
To read the interview in its entirety, click here.