Dynamic ergonomic workload modeling to support workforce-aware scheduling in home health care services

Background Home health care (HHC) services are expanding rapidly as health systems respond to population ageing, increasing prevalence of chronic conditions, and efforts to shift care delivery from hospitals to community settings. While these services improve accessibility and patient satisfaction, they also introduce significant workforce planning challenges. In particular, nurses providing home-based care often work in highly variable environments that can influence both physical and psychosocial workload. Despite these realities, most existing scheduling approaches in home health care focus primarily on operational efficiency indicators such as travel time, service duration, or cost. As a result, ergonomic and contextual factors that shape nurses’ workload are rarely considered in planning decisions, potentially leading to schedules that are operationally efficient but uneven in terms of staff workload and well-being. Methods This study develops a decision-support framework designed to incorporate ergonomic workload considerations into home health care scheduling. First, nurses’ perceived workload following patient visits is captured through a structured post-task assessment that evaluates multiple categories of stressors encountered during care delivery. These assessments are converted into quantitative workload scores using a fuzzy inference system that accommodates the subjective and linguistic nature of workload perceptions. To account for temporal variability in workload exposure, a multi-state Markov modeling approach is then used to estimate transitions between different workload states across consecutive visits. The resulting workload estimates are incorporated into a goal programming–based scheduling model that simultaneously considers patient demand satisfaction and equitable distribution of workload among nurses. Results Computational experiments were conducted using simulated home care scenarios of varying sizes to explore how the integration of dynamic workload information influences scheduling decisions. The results indicate that incorporating ergonomic workload estimates enables more balanced allocation of tasks across nurses while maintaining acceptable levels of service coverage. By adjusting workload limits and objective weights, decision makers can explicitly manage trade-offs between maximizing the number of completed visits and limiting excessive workload exposure for individual staff members. Conclusions Integrating dynamic ergonomic workload information into scheduling decisions provides a more comprehensive approach to workforce planning in home health care services. The proposed framework demonstrates how operational planning models can incorporate contextual and human-centered workload factors alongside traditional efficiency objectives. Such approaches may help health care organizations design more sustainable service delivery systems that protect workforce well-being while continuing to meet growing patient demand.