Patient diversion using real-time delay predictions across healthcare facility networks

This work demonstrates how real-time delay prediction can be used to determine patient diversion across a healthcare facility network. This work presents diversion mechanisms based on real-time predictions of delays at the facilities from which the patient is being diverted as well as at the facility to which diversion is planned. This involves predicting real-time delays not only at the point in time at which the patient arrives at the facility of origin, but also at the near future time point at which the patient may arrive at the facility considered for diversion. Both actual delays and delay predictions based on system state information such as queue length and elapsed service time are considered in the implementation of our proposed diversion mechanism. The implementation of the diversion mechanism is illustrated via a discrete-event simulation of a network of nine primary healthcare facilities in a given region. Diversion is implemented for childbirth patients and inpatients treated at these facilities. As part of this, a novel approximate real-time delay predictor is developed for the queuing systems represented by the childbirth and inpatient care processes, and its performance is compared to existing delay predictors for these queuing systems. With regard to simulation experiments, the conditions under which generation of delay predictions in the near future is relevant is first investigated. The proposed diversion mechanism is simulated, and it is shown that the extent to which operational outcomes become equitably distributed across the PHC networks depends upon the accuracy of the delay predictor.