Imaging 3.0 Meets Artificial Intelligence

Artificial intelligence provides another tool in the Imaging 3.0 toolkit.

 

For the past five years, ACR’s Imaging 3.0 initiative has been the toolkit that we, as radiologists, have used to enhance our value beyond our interpretations to be better stewards of imaging appropriateness, provide a more patient-centered focus within our practices, and prepare for the evolution of health care financing and federal payment policy. Imaging 3.0 continues to challenge us to take ownership of our patients’ entire imaging experience, and now, we have a new tool in the kit that will help us further increase the value we bring to patient care at each step in the imaging value chain: artificial intelligence (AI).

In addition to a focus on consultation, communication, and appropriateness, informatics has played a vital role in our ability to integrate Imaging 3.0 tools into our clinical workflow. And with the widespread availability of patient data from sources like electronic health records, genomics, and even personal electronic devices, the time has come to access these important data elements and bring them to bear on our patients’ imaging care. This is where AI comes into play.

In the mold of past College efforts, like supporting the development of clinical decision support technology, the ACR Data Science Institute, can play a leading role in working with industry to create AI algorithms that will significantly improve the care we provide our patients. For example, AI algorithms that integrate data from an array of electronic sources can help define the subset of patients who can benefit the most from medical imaging — perhaps even before the patient’s primary care physician considers imaging or the patient develops symptoms.

In addition, AI has the potential to provide benefits throughout the imaging care process. During the examination, AI may be able to automatically adjust protocols when patient motion is detected. AI algorithms might also detect a critical abnormality and alert the radiologist that an expedited interpretation or additional imaging test may be in order before the patient even leaves the department.

During our interpretations, AI may help us more reliably detect subtle abnormalities, characterize disease patterns in greater detail, and more accurately measure lesion changes in response to therapy. And finally, AI can enhance the way we communicate by integrating “non-visual” quantitative information from the images into our reports as well as providing pathways to remind our patients and their physicians of needed follow-up examinations.

In these and other ways, AI will become a powerful adjunct to Imaging 3.0 that we should all embrace. With AI tools assisting us, we are poised to provide even better care and further increase our value to our referring physicians, health systems, and patients.

By Bibb Allen Jr, MD, FACR, ACR DSI Chief Medical Officer

Suggested Reading

Imaging 3.0: What is it?
Changing Platitudes to Attitudes: Making the Imaging 3.0 Culture Stick
Adding Value Isn’t an Option Anymore