Ethics in conversation: Building an ethics assurance case for autonomous AI-enabled voice agents in healthcare

The deployment and use of AI systems should be both safe and broadly ethically acceptable. The principles-based ethics assurance argument pattern is one proposal in the AI ethics landscape that seeks to support and achieve that aim. The purpose of this argument pattern or framework is to structure reasoning about, and to communicate and foster confidence in, the ethical acceptability of uses of specific real-world AI systems in complex socio-technical contexts. This paper presents the interim findings of a case study applying this ethics assurance framework to the use of Dora, an AI-based telemedicine system, to assess its viability and usefulness as an approach. The case study process to date has revealed some of the positive ethical impacts of the Dora platform, as well as unexpected insights and areas to prioritise for evaluation, such as risks to the frontline clinician, particularly in respect of clinician autonomy. The ethics assurance argument pattern offers a practical framework not just for identifying issues to be addressed, but also to start to construct solutions in the form of adjustments to the distribution of benefits, risks and constraints on human autonomy that could reduce ethical disparities across affected stakeholders. Though many challenges remain, this research represents a step in the direction towards the development and use of safe and ethically acceptable AI systems and, ideally, a shift towards more comprehensive and inclusive evaluations of AI systems in general.