A systematic review of collaborative robots for nurses: where are we now, and where is the evidence?

Introduction: Robots present an opportunity to enhance healthcare delivery. Rather than targeting complete automation and nurse replacement, collaborative robots, or "cobots", might be designed to allow nurses to focus on high-value caregiving. While many institutions are now investing in these platforms, there is little publicly available data on how cobots are being developed, implemented, and evaluated to determine if and how they support nursing practice in the real world. Methods: This systematic review investigates the current state of cobotic technologies designed to assist nurses in hospital settings, their intended applications, and impacts on nurses and patient care. A comprehensive database search identified 28 relevant peer-reviewed articles published since 2018 which involve real studies with robotic platforms in simulated or actual clinical contexts. Results: Few cobots were explicitly designed to reduce nursing workload through administrative or logistical assistance. Most included studies were designed as patient-centered rather than nurse-centered, but included assistance for tasks like medication delivery, vital monitoring, and social interaction. Most applications emerged from India, with limited evidence from the United States despite commercial availability of nurse-assistive cobots. Robots ranged from proof-of-concept to commercially deployed systems. Discussion: This review highlights the need for further published studies on cobotic development and evaluation. A larger body of evidence is needed to recognize current limitations and pragmatic opportunities to assist nurses and patients using state-of-the-art robotics. Human-centered design can assist in discovering the right opportunities for cobotic assistance. Committed research-practice partnerships and human-centered design are needed to guide the technical development of nurse-centered cobotic solutions.

Towards human-centered AI and robotics to reduce hospital falls: finding opportunities to enhance patient-nurse interactions during toileting.

Introduction: Patients who are hospitalized may be at a higher risk for falling, which can result in additional injuries, longer hospitalizations, and extra cost for healthcare organizations. A frequent context for these falls is when a hospitalized patient needs to use the bathroom. While it is possible that "high-tech" tools like robots and AI applications can help, adopting a human-centered approach and engaging users and other affected stakeholders in the design process can help to maximize benefits and avoid unintended consequences. Methods: Here, we detail our findings from a human-centered design research effort to investigate how the process of toileting a patient can be ameliorated through the application of advanced tools like robots and AI. We engaged healthcare professionals in interviews, focus groups, and a co-creation session in order to recognize common barriers in the toileting process and find opportunities for improvement. Results: In our conversations with participants, who were primarily nurses, we learned that toileting is more than a nuisance for technology to remove through automation. Nurses seem keenly aware and responsive to the physical and emotional pains experienced by patients during the toileting process, and did not see technology as a feasible or welcomed substitute. Instead, nurses wanted tools which supported them in providing this care to their patients. Participants envisioned tools which helped them anticipate and understand patient toileting assistance needs so they could plan to assist at convenient times during their existing workflows. Participants also expressed favorability towards mechanical assistive features which were incorporated into existing equipment to ensure ubiquitous availability when needed without adding additional mass to an already cramped and awkward environment. Discussion: We discovered that the act of toileting served more than one function, and can be viewed as a valuable touchpoint in which nurses can assess, support, and encourage their patients to engage in their own recovery process as they perform a necessary and normal function of life. While we found opportunities for technology to make the process safer and less burdensome for patients and clinical staff alike, we believe that designers should preserve and enhance the therapeutic elements of the nurse-patient interaction rather than eliminate it through automation.

Inclusion of Clinicians in the Development and Evaluation of Clinical Artificial Intelligence Tools: A Systematic Literature Review.

The application of machine learning (ML) and artificial intelligence (AI) in healthcare domains has received much attention in recent years, yet significant questions remain about how these new tools integrate into frontline user workflow, and how their design will impact implementation. Lack of acceptance among clinicians is a major barrier to the translation of healthcare innovations into clinical practice. In this systematic review, we examine when and how clinicians are consulted about their needs and desires for clinical AI tools. Forty-five articles met criteria for inclusion, of which 24 were considered design studies. The design studies used a variety of methods to solicit and gather user feedback, with interviews, surveys, and user evaluations. Our findings show that tool designers consult clinicians at various but inconsistent points during the design process, and most typically at later stages in the design cycle (82%, 19/24 design studies). We also observed a smaller amount of studies adopting a human-centered approach and where clinician input was solicited throughout the design process (22%, 5/24). A third (15/45) of all studies reported on clinician trust in clinical AI algorithms and tools. The surveyed articles did not universally report validation against the "gold standard" of clinical expertise or provide detailed descriptions of the algorithms or computational methods used in their work. To realize the full potential of AI tools within healthcare settings, our review suggests there are opportunities to more thoroughly integrate frontline users' needs and feedback in the design process.

Designing healthcare for human use: Human factors and practical considerations for the translational process.

In recent years, the focus of implementation science (IS) shifted to emphasize the influence of contextual factors on intervention adaptations in clinical, community, and corporate settings. Each of these settings represent a unique work system with varying contexts that influence human capabilities, needs, and performance (otherwise known as "human factors"). The ease of human interaction with a work system or an intervention is imperative to IS outcomes, particularly adoption, implementation, and maintenance. Both scientific approaches consider the "big picture" when designing interventions for users and stakeholders to improve work and health outcomes. IS and human factors are therefore complementary in nature. In this paper, the authors will (1) provide perspective on the synergistic relationship between human factors and IS using two illustrative and applied cases and (2) outline practical considerations for human factors-based strategies to identify contextual factors that influence intervention adoption, implementation, and maintenance dimensions of the RE-AIM framework. This article expands on recent research that developed user- and human-centered design strategies for IS scientists to use. However, defining the complementary relationship between IS and human factors is a necessary and valuable step in maximizing the effectiveness of IS to transform healthcare. While IS can complement practitioners' identification of intervention adaptations, human interaction is a process in the work system often overlooked throughout implementation. Further work is needed to address the influence that organizational endorsement and trust have on intervention adaptations and their translation into the work system.

Behavioral Cues of Humanness in Complex Environments: How People Engage With Human and Artificially Intelligent Agents in a Multiplayer Videogame.

The development of AI that can socially engage with humans is exciting to imagine, but such advanced algorithms might prove harmful if people are no longer able to detect when they are interacting with non-humans in online environments. Because we cannot fully predict how socially intelligent AI will be applied, it is important to conduct research into how sensitive humans are to behaviors of humans compared to those produced by AI. This paper presents results from a behavioral Turing Test, in which participants interacted with a human, or a simple or "social" AI within a complex videogame environment. Participants (66 total) played an open world, interactive videogame with one of these co-players and were instructed that they could interact non-verbally however they desired for 30 min, after which time they would indicate their beliefs about the agent, including three Likert measures of how much participants trusted and liked the co-player, the extent to which they perceived them as a "real person," and an interview about the overall perception and what cues participants used to determine humanness. T-tests, Analysis of Variance and Tukey's HSD was used to analyze quantitative data, and Cohen's Kappa and χ2 was used to analyze interview data. Our results suggest that it was difficult for participants to distinguish between humans and the social AI on the basis of behavior. An analysis of in-game behaviors, survey data and qualitative responses suggest that participants associated engagement in social interactions with humanness within the game.