The American College of Radiology Data Science Institute (ACR DSI) is seeking industry feedback on the first artificial intelligence (AI) use cases in its TOUCH-AI library.
The ACR DSI will consider the feedback before the scheduled release this fall of the use cases. The cases will define exactly how AI algorithms will receive information -- such as images, data from electronic health records, structured data, or unstructured data -- from the clinical workflow, run the AI model, and provide specific outputs such as detection, classification, quantification, and prioritization of information to end users, according to the organization.
These use cases will also provide specific parameters for how AI algorithms will be trained, tested, and validated for regulatory approval and clinical use, as well as for how they will be deployed clinically within existing workflows and how their effectiveness can be monitored. The institute said it has solicited input on the use cases from medical specialties and standards organizations, as well as a variety of AI, analytics, reporting system, electronic medical record, and PACS vendors. The use cases will be freely available upon release in the ACR DSI TOUCH-AI library.
