Deep learning architecture to predict daily hospital admissions

Air pollution and airborne pollen play a key role in respiratory and circulatory disorders and thus have a direct relation to hospital admissions for these causes. Knowing in advance the influx of patients to emergency services allows clinical institutions to optimize resources and to improve their service. Since the variables influencing respiratory and circulatory-related hospital admissions belong to fields such aerobiology or meteorology, we aim for a data-based system which is able to predict admissions without a priori assumptions. Given the number and distribution of observation stations (meteorological, pollen and chemical pollution stations and hospital), previous approaches generate many model-dependent systems that need to be combined in order to obtain the full representation of future environmental conditions. A unified approach able to extract all temporal dynamics as well as all spatial relations would allow a better representation of the aforementioned conditions and consequently a more precise hospital admissions forecast. The proposed system is based on a specific neural network topology of long short-term memories and convolutional neural networks to obtain the spatio-temporal relations between all independent and target variables. It was applied to forecast daily hospital admissions due to respiratory- and circulatory-related disorders. The proposal outperforms the benchmark approaches by reducing as an average the prediction error by 28% and 20% for the circulatory and respiratory cases, respectively. Consequently, the system extracts all relevant information without specific field knowledge and provides accurate hospital admissions forecasts.