Forecasting in Unscheduled care services
My study seeks to improve the efficiency of unplanned care by identifying sources of uncertainty, building a precise and reliable forecasting framework appropriate for decision-making, and detecting potential crowding characteristics.
We intend to address numerous issues that unplanned care services may be facing at the moment:
To find different factors that may affect demand and service and incorporate these factors into predictive models;
To make an accurate prediction of unscheduled care patients flow by using historical time series;
To use machine learning techniques to transform transactional data into meaningful inputs into a predictive model;
To link predictive modeling to decisions in Emergency department and Ambulance services, in a pilot hospital such as Bridgend Hospital in Wales, which optimizes decision making process.