Artificial Intelligence in Cardiovascular Imaging: "Unexplainable" Legal and Ethical Challenges?

Abstract

Nowhere is the influence of artificial intelligence (AI) likely to be more profoundly felt than in health care, from patient triage and diagnosis to surgery and follow-up. Over the medium-term, these effects will be more acute in the cardiovascular imaging context, in which AI models are already successfully performing at approximately human levels of accuracy and efficiency in certain applications. Yet, the adoption of unexplainable AI systems for cardiovascular imaging still raises significant legal and ethical challenges. We focus in particular on challenges posed by the unexplainable character of deep learning and other forms of sophisticated AI modelling used for cardiovascular imaging by briefly outlining the systems being developed in this space, describing how they work, and considering how they might generate outputs that are not reviewable by physicians or system programmers. We suggest that an unexplainable tendency presents 2 specific ethico-legal concerns: (1) difficulty for health regulators; and (2) confusion about the assignment of liability for error or fault in the use of AI systems. We suggest that addressing these concerns is critical for ensuring AI's successful implementation in cardiovascular imaging.