JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) holds the promise to support nurses’ clinical decision making in complex care situations or to conduct tasks that are remote from direct patient interaction such as documentation processes. There has been an increase in research and development of AI applications for nursing care, but a persistent lack of an extensive overview covering the evidence-base for promising application scenarios.

Objective:

The paper synthesizes literature on application scenarios for AI in nursing care settings, as well as highlighting adjacent aspects in the ethical, legal and social discourses surrounding the application of AI in nursing care.

Methods:

Following a rapid review design, databases PubMed, CINAHL, ACM Digital Library, IEEE Xplore, DBLP, and AIS Library, as well as the libraries of leading conferences were searched in June 2020. Publications of quantitative and qualitative original research, systematic reviews, or discussion papers and essays on ethical, legal, and social implications were eligible for inclusion. Based on predetermined selection criteria, eligible studies were analyzed.

Results:

Titles and abstracts of 6,818 publications and 699 fulltexts were screened and 285 publications have been included. Hospitals were the most prominent setting, followed by independent living-at-home, whereas less application scenarios for nursing homes or homecare were identified. Most studies employed machine learning algorithms while expert or hybrid systems were entailed in less than every tenth publication. Application context focused on image and signal processing with tracking, monitoring or classification of activity and health followed by care coordination and communication as well as fall detection was the main purpose of AI applications. Few studies reported effects for clinical or organizational outcomes of AI applications, lacking particularly in data gathered outside of laboratory conditions. Aside from technological requirements, reporting on requirements captures more overarching topics such as data privacy, safety or technology acceptance. Ethical, legal and social implications reflected the discourse on technology use in health care, but have gone mostly undiscussed in detail.

Conclusions:

The results highlight potential for the application of AI systems in different care settings. With regard to the lack of findings on effectiveness and application of AI systems in real-world scenarios, future research should reflect on a more nursing care specific perspective on objectives, outcomes and benefits. We find an advancement in the technological-societal discourse, surrounding the ethical and legal implications of AI applications in nursing care, to be a practical and needed next step for similar research groups. Further, we outline the need for a greater participation among stakeholders. Clinical Trial: not applicable