Abstract:
Healthcare is essential to the general welfare of society. It provides for the prevention, treatment, and management of illness and the preservation of mental and physical well-being through the services offered by medical and allied health professions. Hospitals crowding causes a series of negative effects, e.g. medical errors, poor patient treatment and general patient dissatisfaction. In light of these challenges, a need for review and reform of our healthcare practices has become apparent. One road to improve the typical clinical system is to describe the patient flow in a model of the system and how the system is constrained by available equipment, beds and personnel. Various predictive control models have been developed to try and ease overcrowding in hospitals. Such model is the Model Predictive Control to control the queuing systems developed by Yang Wang and Stephen Boyd. The problem with this model is that it is very slow, work offline and thus not very effective. Others are queuing systems, e.g. dynamic programming and Lagrange approach of adaptive control based on Markov Chain model. In this study the research has compared the existing prediction models and come up with Monte Carlo Simulation model to predict the number of patients in the queue. The model uses Poisson distribution on arrival and exponential distribution on service time. The model is constructed using R program where after running, it generate random numbers. After several experiments the model has proved to be very accurate and efficient. This will assist the hospital to utilize the resources and reduces cost of operations.
