Forecasting emergency department admissions

The emergency department of a hospital plays an extremely important role in the healthcare of patients. To maintain a high quality service, clinical professionals need information on how patient flow will evolve in the immediate future. With accurate emergency department forecasts it is possible to better manage available human resources by allocating clinical staff before peak periods, thus preventing service congestion, or releasing clinical staff at less busy times. This paper describes a solution developed for the presentation of hourly, four-hour, eight-hour and daily number of admissions to a hospital’s emergency department. A 10-year history (2009–2018) of the number of emergency admissions in a Portuguese hospital was used. To create the models several methods were tested, including exponential smoothing, SARIMA, autoregressive and recurrent neural network, XGBoost and ensemble learning. The models that generated the most accurate hourly time predictions were the recurrent neural network with one-layer (sMAPE = 23.26%) and with three layers (sMAPE = 23.12%) and XGBoost (sMAPE = 23.70%). In terms of efficiency, the XGBoost method has by far outperformed all others. The success of the recurrent neuronal network and XGBoost machine learning methods applied to the prediction of the number of emergency department admissions has been demonstrated here, with an accuracy that surpasses the models found in the literature.

Sequence memory in recurrent neuronal network can develop without structured input

How does spontaneous activity during development prepare cortico-cortical connections for sensory input? We here analyse the development of sequence memory, an intrinsic feature of recurrent networks that supports temporal perception. We use a recurrent neural network model with homeostatic and spike-timing-dependent plasticity (STDP). This model has been shown to learn specific sequences from structured input. We show that development even under unstructured input increases unspecific sequence memory. Moreover, networks “pre-shaped” by such unstructured input subsequently learn specific sequences faster. The key structural substrate is the emergence of strong and directed synapses due to STDP and synaptic competition. These construct self-amplifying preferential paths of activity, which can quickly encode new input sequences. Our results suggest that memory traces are not printed on a tabula rasa, but instead harness building blocks already present in the brain.