February 7, 2018 — A U.S. Food and Drug Administration (FDA)-funded program to speed safe and effective medical device technologies to market has chosen an ACR Data Science Institute (DSI) use case among its first demonstration projects.
The National Evaluation System for Health Technology Coordinating Center (NESTcc) selected the “Lung-RADS Assist: Advanced Radiology Guidance, Reporting and Monitoring” use case. The center supports timely, reliable and cost-effective evidence development regarding FDA medical device pre- and post-market requirements.
“We are proud that the NEST program recognizes the value of the ACR Data Science Institute’s groundbreaking work. The ACR DSI will employ our open framework, TOUCH-AI (Technology Oriented Use Cases for Healthcare Artificial Intelligence), to provide infrastructure for ongoing longitudinal AI algorithm verification pre- and post-FDA approval. This can help bring better medical care to patients more quickly,” said ACR DSI Chief Medical Officer Bibb Allen Jr., M.D., FACR.
Lung-RADS Assist will determine the end-to-end workflow from deployment of an AI algorithm in a radiology reporting system through capture of performance metrics within a national registry. It will:
- Utilize existing ACR technology to demonstrate the ability to collect validation data and perform local algorithm testing prior to market approval;
- Utilize existing ACR technology to facilitate interoperability between reporting and AI vendors to generate standardized data in a real-world setting; and
- Capture validation data and real-world events in a national registry to enable both facility-level and cross-facility reporting.
“The future of medical imaging is doctors harnessing the power of AI to enhance their decision making. New and existing technologies will provide greater detection and treatment by using all available data to improve patient -centered care. The ACR DSI provides a national foundation to move this process forward,” said Keith J. Dreyer, DO, Ph.D., FACR, ACR DSI chief science officer.
Use cases are clinical scenarios in which artificial intelligence (AI) use may improve care. Defining these cases is a first step in the creation of AI algorithms to answer primary clinical questions in each case. Medical imaging AI use case development is an initial focus of the ACR DSI. The DSI was launched in May 2017 to develop and use AI to help radiologists improve medical imaging care.
The first NESTcc demonstration projects will develop, verify and operationalize methods of evidence generation and data use. The projects will build out critical functions and processes to sustain the NEST program.
For more information: www.nestcc.org
