In October, 2006, I posted a blog note suggesting that pathology should consider merging with radiology. The idea gave a number of people indigestion; one pathology chairman described it to me as a bridge too far (see: Ten Reasons for Merging Pathology/Lab Medicine with Radiology). In the interval of nearly 13 years a number of changes have occurred in the two fields and the idea "may" have gained some cautious supporters -- one of them perhaps may be the blogger Dimitri Merine who posted a note in the JACR Blog in December, 2018, that provided a balanced discussion of the idea (see: Radpathology/Pathradiology: The Information Specialty of The Future?). Below is an excerpt of his article:
Welcome to the Imaging 5.0 uber-super physician who is both radiologist and pathologist. The image centric disciplines of radiology and pathology (rad-path) are ripe for disruption. Analyzing images is a perfect fit for AI, potentially redefining the two disciplines. Artificial intelligence (AI) will change radiology and pathology, likely forcing them to consider merging. One audacious and futuristic proposal to survive the AI robopocalypse is the merger of the two specialties. In a 2016 JAMA editorial, Drs Saurabh Jha...and Eric Topol...proposed a fusion of diagnostic radiology/molecular imaging and pathology/laboratory medicine into a unified "information specialist" discipline.
Surprisingly, this was not a new idea. Richard Friedberg MD championed the idea as far back as 1997 when he created a unified Diagnostic Medicine Service (combining pathology, radiology, and nuclear medicine) within the Department of Veteran Affairs, known as the VA Southeast Network. In 2006, Bruce Friedman, a prominent pathologist, made a compelling argument for unification and presented "Ten reasons for merging pathology/lab medicine with radiology." Among the benefits he envisioned are "integrated reports of pathologists and radiologists working collaboratively" and "higher levels of quality." A former executive of General Electric made a similar argument in 2007.
Here is a list of some new ideas and considerations regarding the possible merger of pathology and radiology into one specialty, perhaps called Diagnostic Medicine:
- Digital pathology has become much more of a reality in the intervening years. I would predict that the majority of academic and large hospital pathology departments will deploy this technology in the next five years. Therefore, much of surgical pathology (to come) and all of radiology imaging (now) will be digital.
- Serous discussion in the past has focused on the development of enterprise image servers that would support both pathology and radiology images (see: PACS (picture archiving and communication system)). I can't find much discussion about this on the web so maybe this idea is not yet practical.
- Radiology and pathology will be the first medical specialties to broadly deploy AI systems closely integrated with workflow, more specifically deploying image analysis software. For pathology, I think that the most promising systems will identify fields of interest in each surgical pathology case being reviewed by a pathologist, thus reducing the time spent per slide.
- For those health systems wanting to "dip a toe" into closer collaboration between radiology and pathology, I previously suggested in a blog note that a concordance conference should be launched in most hospitals for discussion of complex cases with a review of both radiology and surgical pathology reports (see: Pathology and Radiology Collaborate with a Concordance Conference). The goal is to identify those cases where complete concordance (i.e., agreement) in reporting is not achieved and discuss why this has occurred. In the process, mistakes will inevitably be uncovered.
Comments