A Framework for Self-Explaining Systems in the Context of Intensive Care

ABSTRACT

Ventilated intensive care patients represent a sizable group in the intensive care unit that requires special attention. Although intensive care units are staffed with more nurses per patient than regular wards, the situation is often precarious. A situation that has become more acute during the COVID-19 pandemic. Weaning from mechanical ventilation as well as the limited communication abilities pose substantial stress to the patients. The incapability to impart even basic needs may negatively impact the healing process and can lead to delirium and other complications. To support the communication and information of weaning patients as well as to foster patient autonomy, we are developing a smart environment that is tailored to the intensive care context. While the provision and connection of smart objects and applications for this purpose can be timeconsuming, self-organization and self-explainability may present helpful tools to reduce the effort. In this paper, we present a framework for self-explaining and semi-automatically interconnected ensembles of smart objects and ambient applications (that are integrated into smart spaces) used to realize the assistive environment. Based on a description language for these components, ensembles can be dynamically connected and tailored to the needs and abilities of the patients. Our framework has been developed and evaluated iteratively and has been tested successfully in our laboratory.