AI Interventions to Alleviate Healthcare Shortages and Enhance Work Conditions in Critical Care: Qualitative Analysis

Abstract

Background: The escalating global scarcity of skilled health care professionals is a critical concern, further exacerbated by rising stress levels and clinician burnout rates. Artificial intelligence (AI) has surfaced as a potential resource to alleviate these challenges. Nevertheless, it is not taken for granted that AI will inevitably augment human performance, as ill-designed systems may inadvertently impose new burdens on health care workers, and implementation may be challenging. An in-depth understanding of how AI can effectively enhance rather than impair work conditions is therefore needed.

Objective: This research investigates the efficacy of AI in alleviating stress and enriching work conditions, using intensive care units (ICUs) as a case study. Through a sociotechnical system lens, we delineate how AI systems, tasks, and responsibilities of ICU nurses and physicians can be co-designed to foster motivating, resilient, and health-promoting work.

Methods: We use the sociotechnical system framework COMPASS (Complementary Analysis of Sociotechnical Systems) to assess 5 job characteristics: autonomy, skill diversity, flexibility, problem-solving opportunities, and task variety. The qualitative analysis is underpinned by extensive workplace observation in 6 ICUs (approximately 559 nurses and physicians), structured interviews with work unit leaders (n=12), and a comparative analysis of data science experts' and clinicians' evaluation of the optimal levels of human-AI teaming.

Results: The results indicate that AI holds the potential to positively impact work conditions for ICU nurses and physicians in four key areas. First, autonomy is vital for stress reduction, motivation, and performance improvement. AI systems that ensure transparency, predictability, and human control can reinforce or amplify autonomy. Second, AI can encourage skill diversity and competence development, thus empowering clinicians to broaden their skills, increase the polyvalence of tasks across professional boundaries, and improve interprofessional cooperation. However, careful consideration is required to avoid the deskilling of experienced professionals. Third, AI automation can expand flexibility by relieving clinicians from administrative duties, thereby concentrating their efforts on patient care. Remote monitoring and improved scheduling can help integrate work with other life domains. Fourth, while AI may reduce problem-solving opportunities in certain areas, it can open new pathways, particularly for nurses. Finally, task identity and variety are essential job characteristics for intrinsic motivation and worker engagement but could be compromised depending on how AI tools are designed and implemented.

Conclusions: This study demonstrates AI's capacity to mitigate stress and improve work conditions for ICU nurses and physicians, thereby contributing to resolving health care staffing shortages. AI solutions that are thoughtfully designed in line with the principles for good work design can enhance intrinsic motivation, learning, and worker well-being, thus providing strategic value for hospital management, policy makers, and health care professionals alike.

Keywords: AI; ICU; artificial intelligence; autonomy; burden; burnout; competence; employee; flexible; future of work; health care professional; health care professionals; hospital; intensive care; job; new work; occupational health; overburdened; satisfaction; sociotechnical; sociotechnical system; stress; stress mitigation; task; work; work design; worker; workplace.

Figure 1

Five job characteristics for motivating, resilient, and health-promoting work.

Figure 2

Summary of results from Bienefeld et al [39], a mixed-method study identifying optimal levels of human-AI teaming in a sample of n=19 data science experts and n=61 nurses and physicians. AI: artificial intelligence.

Figure 3

Summary of AI-induced changes to key job characteristics, based on a comparative analysis of ICU nurses’ and physicians’ work with versus without AI combining observational data (approximately 559 ICU nurses and physicians) and data from structured interviews (n=12 ICU head nurses and physicians). Arrows pointing to the right signify an improvement; arrows to the left a deterioration. The equal sign signifies no change. Nurse-specific changes are displayed in orange; physician-specific changes are in blue. The category “Nurses” includes only registered nurses. The category “Physicians” combines resident and attending physicians. AI: artificial intelligence; COMPASS: Complementary Analysis of Sociotechnical Systems; ICU: intensive care unit.