PROJECT TITLE :

Intelligent Patient Management and Resource Planning for Complex, Heterogeneous, and Stochastic Healthcare Systems

ABSTRACT:

Effective resource requirement forecasting is critical to reduce the escalating price of care by guaranteeing optimum utilization and availability of scarce health resources. Patient hospital length of stay (LOS) and therefore resource needs depend on several factors together with covariates representing patient characteristics like age, gender, and diagnosis. We have a tendency to so propose the employment of such covariates for better hospital capacity coming up with. Likewise, estimation of the patient's expected destination after discharge can facilitate in allocating scarce community resources. Additionally, probable discharge destination might well affect a patient's LOS in hospital. As an example, it may be needed to delay the discharge of a patient therefore as to form acceptable care provision within the community. A number of deterministic models such as ratio-based ways have failed to address inherent variability in advanced health processes. To handle such complexity, various stochastic models have so been proposed. However, such models fail to consider inherent heterogeneity in patient behavior. Therefore, we tend to here use a part-kind survival tree for teams of patients that are homogeneous with respect to LOS distribution, on the idea of covariates like time of admission, gender, and disease diagnosed; these homogeneous groups of patients can then model patient flow through a care system following stochastic pathways that are characterized by the covariates. Our section-type model is then extended by more growing the survival tree primarily based on covariates representing outcome measures like treatment outcome or discharge destinations. These extended part-sort survival trees are terribly effective in modeling interrelationship between a patient's LOS and such outcome measures and allow us to explain patient movements through an integrated care system together with hospital, social, and community elements. During this paper, we 1st propose a generalization of the Coxian part-sort distribution to a - arkov method with more than one absorbing state; we tend to call this the multi-absorbing state section-sort distribution. We tend to then describe how the model will be used with the extended section-kind survival tree for forecasting hospital, social, and community care resource requirements, estimating price of care, predicting patient demography at a given time in the longer term, and admission scheduling. We tend to can, so, provide a stochastic approach to capacity planning across complicated heterogeneous care systems. The approach is illustrated using a 5 year retrospective data of patients admitted to the stroke unit of the Belfast City Hospital.