This browser is not actively supported anymore. For the best passle experience, we strongly recommend you upgrade your browser.
Welcome to Reed Smith's viewpoints — timely commentary from our lawyers on topics relevant to your business and wider industry. Browse to see the latest news and subscribe to receive updates on topics that matter to you, directly to your mailbox.
| 2 minutes read

Structured vs. free text indications for advanced imaging orders? Or both?

It is inspiring to see innovative uses of technology come into play to meet the some of the challenges faced by radiology practices. In this case, artificial intelligence (AI) may help solve a thorny barrier to the effective implementation of a Medicare program set to begin next year.

The appropriate use criteria (AUC) program resulting from the Protecting Access to Medicare Act (PAMA) enacted in 2014 – which relates to physicians who order outpatient advanced diagnostic imaging (MRI, CT, PET, and nuclear medicine) studies for Medicare beneficiaries – is set to be fully implemented in 2022. The program requires the physician who places orders for advanced imaging to review AUC by making use of a clinical decision support (CDS) system approved by the Centers for Medicaid and Medicaid Services. When consulting the CDS, the physician can then review an array of indications that map to AUC to determine if the exam is "appropriate" or not. 

A major challenge that has arisen in the effective implementation of AUC in many institutions has been the proliferation of unstructured "free text" entries from the ordering physician if a matching predefined indication is not readily available via the CDS. The appropriateness of structured indications can be scored, but free-text indications cannot. Consequently, radiology departments have been developing strategies to minimize free text indications for studies from ordering physicians. 

An interesting approach being used at the Yale School of Medicine to address this challenge was presented this week at the 2021 annual meeting of the Society for Imaging Informatics in Medicine (SIIM21). Dorothy Sippo, MD is an Associate Professor in the Department of Radiology & Biomedical Imaging at Yale.  At SIIM21, Dr. Sippo shared how the CDS challenges caused by free text entries have been dealt with by integrating artificial intelligence (AI) into the order entry process.

In 2020, Yale introduced an AI software that suggests a structured indication to ordering clinicians based on their entry of free text indications, allowing them to then choose a structured indication from the AI's suggested list of indications provided in a pop-up on the software. Radiologists then receive both the free-text and structured indication information once the order is complete.

Dr. Sippo reported that the use of AI delivered a significant improvement in the number of appropriate exam orders. "We were also excited to see that there was a decrease in the number of our unscored orders, which is exactly what we wanted," she said.

Much work remains to be done. But it is impressive to see innovations being employed that embrace the tendency of ordering doctors to make use of free text indications rather than thwart their use altogether.

In addition, the AI capability enabled structured information to be collected from these free-text clinical histories, Sippo said. What's more, the authors learned that it's essential to communicate clearly and broadly to all providers in order for new electronic health record functionality to be successfully adopted, Sippo said.


health care & life sciences, diagnostic imaging, ai, medicare