A first-of-its-kind series of standardized artificial intelligence (AI) use cases from the American College of Radiology Data Science Institute™ (DSI) will accelerate medical imaging AI adoption by ensuring that algorithms:
- Address relevant clinical questions
- Can be implemented across multiple electronic workflow systems
- Enable ongoing quality assessment, and
- Comply with legal, regulatory and ethical requirements
The ACR DSI use cases present a pathway to help AI developers solve health care problems in a comprehensive way that turns concepts for AI solutions into safe and effective tools to help radiologists provide better care for our patients,” said Bibb Allen Jr., MD, FACR, ACR DSI Chief Medical Officer.
“The ACR DSI use cases provide a previously missing understanding with end users on what an AI solution is to deliver by providing functional requirements, and enabling better analysis and test models. This makes it easier for developers to develop algorithms that provide specific information medical professionals need and can be efficiently implemented into clinical practice,” said Rik Primo, Manager of Imaging Informatics Strategic Relationships, Siemens Medical Solutions USA, Inc.
“Clinical insight from the ACR Data Science Institute validates the impact artificial intelligence can have on radiology. The use cases highlight a number of specific opportunities that are supported by value proposition, workflow and dataset details,” said John Axerio-Cilies, chief technology officer at Arterys.
This continually updated, freely available use case series is the product of a previously missing and collaborative framework that enables efficient creation, implementation and ongoing improvement of radiological AI tools.
Specifically – the ACR-DSI Technology Oriented Use Cases in Health Care-AI (TOUCH-AI) Framework:
- Leverages multispecialty, multi-industry expert panels to define clinically relevant use cases for development of medical imaging, interventional radiology and radiation oncology AI algorithms
- Establishes a methodology and provides tools and metrics for creating algorithm training, testing and validation of data sets around these use cases
- Develops standardized pathways for implementing AI algorithms in clinical practice
- Creates opportunities to monitor the effectiveness of AI algorithms in clinical practice through the ACR National Radiology Data Registry, the ACR DSI algorithm monitoring service, Assess-AI and others
- Addresses regulatory, legal and ethical issues regarding medical imaging, interventional radiology and radiation oncology AI
“The ACR DSI framework promotes standardization, interoperability, reportability and patient safety in radiological artificial intelligence development that can help usher in a new era of advanced medicine,” said Keith J. Dreyer, DO, PhD, FACR, ACR DSI Chief Science Officer.
“For AI to deliver on its promise to advance medical imaging, a sustained collaborative effort is required between patients, providers, professional associations, regulators, developers and industry. Working closely with an organization like the ACR Data Science Institute helps us to identify and prioritize the right conditions for use cases most valuable to patient care and greatly amplifies the voice of the customer,” said Thierry Verstraete, Global Product Manager for Analytics & AI, Carestream.
For more information, visit the ACR Data Science Institute website (www.acrdsi.org).