Abstract
This article summarizes existing ethical frameworks for healthcare artificial intelligence (AI) and ambient sensing technology, such as computer vision, and examines their application to improve patient outcomes in the intensive care unit (ICU). Integrating ethical considerations such as privacy, fairness, and autonomy into the lifecycle of an AI tool is necessary to fully harvest AI's potential to deliver safe, high-quality, personalized, and low-cost healthcare services that provide positive experiences for patients, families, and clinicians while improving health outcomes. Drawing from agile science, the article proposes a practical roadmap for clinician and researcher use to identify, integrate, and monitor ethical considerations throughout the lifecycle of an AI tool with the intention to improve patient care. A use case illustrates the application of the agile science-informed roadmap that details the development of a passive digital marker for delirium severity.