Search for: All records

Maintaining an appropriate staffing level is essential to providing a healthy workplace environment at nursing homes and ensuring quality care among residents. With the widespread Covid-19 pandemic, staff absenteeism frequently occurs due to mandatory quarantine and providing care to their inflicted family members. Even though some of the staff show up for work, they may have to perform additional pandemic-related protection duties. In combination, these changes lead to an uncertain reduction in the quantity of care each staff member able to provide in a future shift. To alleviate the staff shortage concern and maintain the necessary care quantity, we study the optimal shift scheduling problem for a skilled nursing facility under probabilistic staff shortage in the presence of pandemic-related service provision disruptions. We apply a two-stage stochastic programming approach to our study. Our objective is to assign staff (i.e., certified nursing aids) to shifts to minimize the total staffing cost associated with contract staff workload, the adjusted workload for the changing resident demand, and extra workload due to required sanitization. Thus, the uncertainties considered arise from probabilistic staff shortage in addition to resident service need fluctuation. We model the former source of uncertainty with a geometric random variable for each staffer. In a proof-of-the-concept study, we consider realistic COVID-19 pandemic response measures recommended by the Indiana state government. We extract payment parameter estimates from the COVID-19 Nursing Home Dataset publicly available by the Centers for Medicare and Medicaid Services (CMS). We conclude with our numerical experiments that when a skilled nursing facility is at low risk of the pandemic, the absenteeism rate and staff workload increase slightly, thus maintaining the current staffing level can still handle the service disruptions. On the other hand, under high-risk circumstances, with the sharp increase of the absence rate and workload, a care facility likely needs to hire additional full-time staff as soon as possible. Our research offers insights into staff shift scheduling in the face of uncertain staff shortages and service disruption due to pandemics and prolonged disasters. 

Trauma continues to be the leading cause of mortality and morbidity among US citizens aged <44 years. Literature suggests that geographical maldistribution of trauma centers (TCs) is associated with increasing fatality rate. Existing models for TC network design do not address the question often raised by trauma decision makers: how many TCs are required to achieve acceptable levels of mistriages? We propose a model to optimize the network of TCs under mistriage constraints. We propose a notional field triage protocol to estimate mistriages (under and over), based on existing guidelines in the trauma literature. Due to the complexity of the underlying model, we propose a Particle Swarm Optimization based solution approach. We use 2012 data from the State of Ohio, and model both ground and air transportation modes. Our results show that, for 2012 mistriage levels, it is possible to reduce the number of TCs from 21 to 10 by distributing them appropriately across urban and rural areas. Further, redistributing these 21 TCs can help satisfy the recommendation of under-triage ≤0.05 by the American College of Surgeons. In general, our study provides trauma decision makers an ability to determine a network that could improve care and/or reduce cost. 

Whether to evacuate a nursing home (NH) or shelter in place in response to the approaching hurricane is one of the most complex and difficult decisions encountered by nursing home administrators. A variety of factors may affect the evacuation decision, including storm and environmental conditions, nursing home characteristics, and the dwelling residents’ health conditions. Successful prediction of evacuation decision is essential to proactively prepare and manage resources to meet the surge in nursing home evacuation demands. In current nursing home emergency preparedness literature, there is a lack of analytical models and studies for nursing home evacuation demand prediction. In this paper, we propose a predictive analytics framework by applying machine learning techniques, integrated with domain knowledge in NH evacuation research, to extract, identify and quantify the effects of relevant factors on NH evacuation from heterogeneous data sources. In particular, storm features are extracted from Geographic Information System (GIS) data to strengthen the prediction accuracy. To further illustrate the proposed work and demonstrate its practical validity, a real-world case study is given to investigate nursing home evacuation in response to recent Hurricane Irma in Florida. The prediction performance among different predictive models are also compared comprehensively.