An Analytics-based Decision Support System for Resource Planning under Heterogeneous Service Demand of Nursing Home Residents

Nursing homes (NHs) are critical healthcare infrastructures for caring frail older adults with 24/7 formal care and personal assistance. Adequate NH resource planning is of great importance to ensure desired quality of care and resident outcomes yet challenging. The challenge lies in the heterogeneous service demand of NH residents, due to the varied individual characteristics, the diverse dwelling duration with multiple competing discharge dispositions, and the diverse service need. Existing healthcare staffing literatures often assumed a homogeneous population of NH residents and neglected the complexity of service demand heterogeneity. This work proposes an analytics-based modeling framework with a userfriendly decision support platform for NH resource planning. The proposed framework characterizes the heterogeneous service demand of NH residents via novel integration of advanced statistical modeling, computer simulation and optimization techniques. We further provide a case study using real data from our industrial collaborator to demonstrate the effectiveness and superior performance of the proposed work. The impacts of service utilization heterogeneity and service need heterogeneity on resource planning decisions are investigated as well. Note to Practitioners This work is motivated by the challenging task of nursing home resource planning under the complex and heterogeneous service demand of nursing home residents. This research work integrates predictive statistical models with computer simulation and optimization techniques to characterize heterogeneous service demand of NH residents at higher modeling fidelity and to facilitate resource planning decision making in response to service demand heterogeneity. The strategies and policies derived from the proposed decision support system are implementable and actionable in current nursing home industry practice. The proposed framework can easily adapt to varied residents census compositions across different nursing facilities or different seasonal periods with minimum adjustment. Moreover, the proposed methodological framework can be extended for resource preparedness and care delivery decisions under extreme event scenarios, such as influenza seasons or pandemic.