A data mining approach for estimating patient demand for health services

Abstract

The ability to better forecast demand for health services is a critical element to maintaining a stable quality of care. Knowing how certain events can impact requirements, health-care service supplier can better assign available resources to more effectively treat patients' needs. The embodiment of data mining analytics can support available data to identify cyclical patterns through relevant variables, and these patterns provide actionable information to adequate decision markers at health-care structures. The request for health-care services can be subject to change from time of year (seasonality) and economic factors. This paper exemplifies the efficacy of data mining analytics in identifying seasonality and economic factors as measured by time that affect patient demand for health-care services. It incorporates a neural network analytic method that is applied over a readily available dataset. The results indicate that day of week, month of year, and a yearly trend significantly impact the demand for patient services.

Keywords

• Data mining
• neuronal networks
• decision support systems
• healthcare IT