While AI remains a hot topic in radiology, much of the attention has been on image interpretation. However, image interpretation is only one part of the imaging value chain, and AI has tremendous potential beyond the interpretation of pixel data. This presentation will explore the non-interpretative use cases of AI from ordering, scheduling, image protocol optimization, imaging modality operations, reporting, quality improvement, billing, communication to the ordering providers and patients, and follow-up management. Recent advancements in natural language processing will be discussed and how they can aid in various aspects of the imaging value chain.
Analytics is another area that has gained increasing interest in recent years and has become a valuable tool for radiology administrators. While many tools are available, radiology practices today use primarily descriptive analytics (i.e., retrospective analysis). With the advances in machine learning, we now can forecast and better utilize predictive and prescriptive analytics. This presentation will also discuss the advances in predictive analytics and how they can be used within radiology practices to improve efficiency and productivity.
Finally, burnout has been an important topic of discussion, with many medical imaging professionals experiencing burnout. While many mitigation strategies for burnout do not involve technology, this presentation will discuss how one can leverage technology to address burnout. This presentation will discuss how one can combine the power of AI and predictive analytics to combat burnout.
Learning Objectives:
Describe non-interpretative use cases of AI in radiology
Examine the benefits of predictive and prescriptive analytics and how they can be used to improve radiology practices
Leverage AI and advanced analytics to combat burnout