On Sept. 25, the ACR Data Science Institute hosted an international group of leading artificial intelligence (AI) experts, AI researchers, medical device vendors and physicians.
This medical imaging AI summit is one of many pacesetting steps the ACR has taken to build consensus around a vendor-neutral DSI framework that helps to ensure the benefits of AI technologies are maximized for improved patient care.
Bibb Allen Jr., MD, FACR, ACR DSI Chief Medical Officer, informed attendees about the role the ACR and its members serve in developing effective AI tools.
Keith J. Dreyer, DO, PhD, FACR, ACR DSI Chief Science Officer, explained how the ACR DSI envisions these technologies being developed, delivered to market and used by radiologists and other physicians.
Much of the discussion centered on ensuring that algorithms developed answered the most relevant clinical questions and the need for an agreed-upon validation strategy necessary for clinical deployment.
The clinical target will be specified in use cases or scenarios that describe how the AI algorithms can be used within the clinical workflow.
Defining these cases is a critical first step in the AI algorithm life-cycle and will be essential to ensure that these tools can be used to improve patient care.
The ACR DSI launched in May 2017 to guide the development of AI algorithms that help radiologists improve medical imaging care (and health care overall) by:
- Defining strategic use case categories to maximize patient care
- Optimizing patient safety, interoperability and regulatory processes
- Promoting the integration of AI solutions into clinical practice
- Providing ongoing AI validation, pre- and post-FDA approval
Stay tuned to the ACR website for more news and information as the work of the ACR Data Science Institute progresses.