Artificial Intelligence in CV Imaging—Translation to Patient Care: Key Points
- Dey D, Arnaout R, Antani S, et al.
- Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care. JACC Cardiovasc Imaging 2023;Jul 19:[Epub ahead of print].
The following are key points to remember from a state-of-the-art paper summarizing proceedings of a National Heart, Lung, and Blood Institute (NHLBI)–led workshop on artificial intelligence (AI) in cardiovascular (CV) imaging;
- AI promises to revolutionize many fields, but its clinical implementation in CV imaging is still rare despite increasing research.
- Access to large, high-quality, diverse datasets drives innovation in AI. Successful data access and sharing will require both technical and policy support at multiple levels, including governmental, institutional, and individual.
- There is a need for developing methods to assess data quality and diversity, data harmonization, and data security, all while also promoting a diverse AI workforce.
- We need to expand methods for data- and label-efficient algorithms, multi-modality algorithms, and for evaluation of AI models’ robustness, generalizability, and learned features; and to develop methods for interoperable and sustainable code across computing platforms that are easy for biomedical researchers to learn and use.
- A highly practical application in CV imaging is assistance in image quantification—a task that is currently subjective and associated with observer variability.
- In regulatory science, there is a need to address the lack of consensus methods for enhancing algorithm training for small clinical datasets, better understand failure modes for AI devices, develop assessment methods to evaluate adaptive and autonomous devices, and forge a clear path to updating AI-based software as a medical device (SaMD) as technology rapidly evolves.
- In addition to regulatory compliance, deployment of AI algorithms in clinical practice must include consideration of effectiveness in real-world settings, workflow integration, trust, and adoption by providers, reimbursement, and continuous monitoring and updating.
- There is a need to formulate clinical trials, health care utilization studies, and other implementation studies to demonstrate AI’s ability to impact clinical outcomes and thus help facilitate payer reception of AI-based tools.
- Improved patient outcomes derived from AI tools would incentivize payers, physicians, hospital administrators, data scientists, and patients alike to adopt and implement their use, especially where reimbursement opportunities may be limited.
- Finally, educating clinicians in AI to improve trust in the methods and thus promote evaluation of AI for clinical cardiology by leading clinical trials and contributing to quality improvement, and engaging societies in the education process, in supporting AI-friendly datasets and registries that are readily accessible to users, and in helping to create guidelines for implementation.
Keywords: Algorithms, Artificial Intelligence, Consensus, Data Science, Deep Learning, Diagnostic Imaging, Intelligence, Machine Learning, Patient Care, Patient Outcome Assessment, Policy, Software, Trust, Workflow, Workforce
< Back to Listings