Over the past year much has been written about the capability of artificial intelligence (AI), and what it will mean for imaging services. At last year’s RSNA, AI was the featured topic and received the lion’s share of publicity.
The glamorous aspect of AI and machine learning has been how AI can assist the radiologist with diagnosis of imaging studies. A key area of focus has been in chest imaging where there has been some success in triaging abnormal chest images. The upside of such applications is improved diagnostic efficiency, particularly as healthcare moves toward value-based care. The downside is that such algorithms require substantial amounts of data to validate, and they will need to go through the FDA approval process, which will take time before they can be fully implemented.
Ultimately, AI imaging applications will pay off. But, what about the other potentially less-glamorous aspect of applying AI/machine learning to the diagnostic process? By that, I am referring to its use in terms of workflow orchestration. Aside from interpreting imaging content, AI/machine learning applied to workflow orchestration can provide valuable information and assistance in preparing a case for interpretation.
Take for example Siemens Healthineer’s AI-Rad Companion application. The application provides automated identification, localization, labeling and measurements for anatomies and abnormalities. Such a capability can improve the radiologist’s efficiency without necessarily employing an algorithm to assess the image.
Other workflow applications can assess the study and mine relevant information from the EHR to present to the radiologist, again with the goal of improving their efficiency and efficacy. Still other applications match radiologist reading assignments with available studies to improve reading efficiency. In another twist, one company has demonstrated a capability to further analyze cases, using AI to assign the next appropriate case to a radiologist without the need for a worklist.
As healthcare providers consolidate, there is a growing need for improvement in resource utilization across facilities. Smart worklists that can present cases to individual radiologists across facilities can improve the overall efficiency and efficacy of interpretation. Rule sets that address radiologist availability, reading sub-specialties, location, etc. can help “level-load” reading resources.
My point is that while AI applications that manipulate images may hold great promise for the future of diagnosis, areas such as workflow orchestration might offer more immediate results in an environment of changing healthcare. Providers should take a close look at these applications to assess whether they can achieve a more immediate impact on imaging operations.