Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods

Forecasting the different types of emergency department (ED) demands (patient flows) in hospital systems much aids ED managers in looking into various options to appropriately allocating the restricted resources available per patient attendance. Deep learning networks have recently gained great succ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Fouzi Harrou, Abdelkader Dairi, Farid Kadri, Ying Sun
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Hospital systems Patient flows ED visits Forecasting Hybrid deep learning methods Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/37f5111959ce4dddaeeaba146515af39
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:37f5111959ce4dddaeeaba146515af39
record_format	dspace
spelling	oai:doaj.org-article:37f5111959ce4dddaeeaba146515af392021-11-22T04:33:09ZEffective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods2666-827010.1016/j.mlwa.2021.100200https://doaj.org/article/37f5111959ce4dddaeeaba146515af392022-03-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666827021001006https://doaj.org/toc/2666-8270Forecasting the different types of emergency department (ED) demands (patient flows) in hospital systems much aids ED managers in looking into various options to appropriately allocating the restricted resources available per patient attendance. Deep learning networks have recently gained great success in modeling time-dependent in time series data. Thus, this work advocates the use of deep learning-driven models for patient flows forecasting. Notably, we examine and compare seven deep learning models, Deep Belief Network (DBN), Restricted Boltzmann machines (RBM), Long Short Term Memory (LSTM), Gated recurrent unit (GRU), combined GRU and convolutional neural networks (CNN-GRU), LSTM-CNN, and Generative Adversarial Network based on Recurrent Neural Networks (GAN-RNN), to forecast patient flow in a hospital emergency department. We introduce a forecaster layer as output for each model to enable traffic flow forecasting. Patient flow data from different ED services, including biology, radiology, scanner, and echography, in Lille regional hospital in France, is used as a case study in assessing the considered forecasting models. Four metrics of effectiveness are adopted for evaluating and comparing the forecasting methods. The results show the promising performance of deep learning models for ED patient flow forecasting compared to shallow methods (i.e., ridge regression and support vector regression). In addition, the results highlighted the superior performance of the DBN compared to the other models by achieving an averaged mean absolute percentage error of around 4.097% and R2 of 0.973.Fouzi HarrouAbdelkader DairiFarid KadriYing SunElsevierarticleHospital systemsPatient flowsED visitsForecastingHybrid deep learning methodsCyberneticsQ300-390Electronic computers. Computer scienceQA75.5-76.95ENMachine Learning with Applications, Vol 7, Iss , Pp 100200- (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hospital systems Patient flows ED visits Forecasting Hybrid deep learning methods Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Hospital systems Patient flows ED visits Forecasting Hybrid deep learning methods Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95 Fouzi Harrou Abdelkader Dairi Farid Kadri Ying Sun Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
description	Forecasting the different types of emergency department (ED) demands (patient flows) in hospital systems much aids ED managers in looking into various options to appropriately allocating the restricted resources available per patient attendance. Deep learning networks have recently gained great success in modeling time-dependent in time series data. Thus, this work advocates the use of deep learning-driven models for patient flows forecasting. Notably, we examine and compare seven deep learning models, Deep Belief Network (DBN), Restricted Boltzmann machines (RBM), Long Short Term Memory (LSTM), Gated recurrent unit (GRU), combined GRU and convolutional neural networks (CNN-GRU), LSTM-CNN, and Generative Adversarial Network based on Recurrent Neural Networks (GAN-RNN), to forecast patient flow in a hospital emergency department. We introduce a forecaster layer as output for each model to enable traffic flow forecasting. Patient flow data from different ED services, including biology, radiology, scanner, and echography, in Lille regional hospital in France, is used as a case study in assessing the considered forecasting models. Four metrics of effectiveness are adopted for evaluating and comparing the forecasting methods. The results show the promising performance of deep learning models for ED patient flow forecasting compared to shallow methods (i.e., ridge regression and support vector regression). In addition, the results highlighted the superior performance of the DBN compared to the other models by achieving an averaged mean absolute percentage error of around 4.097% and R2 of 0.973.
format	article
author	Fouzi Harrou Abdelkader Dairi Farid Kadri Ying Sun
author_facet	Fouzi Harrou Abdelkader Dairi Farid Kadri Ying Sun
author_sort	Fouzi Harrou
title	Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
title_short	Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
title_full	Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
title_fullStr	Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
title_full_unstemmed	Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods
title_sort	effective forecasting of key features in hospital emergency department: hybrid deep learning-driven methods
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/37f5111959ce4dddaeeaba146515af39
work_keys_str_mv	AT fouziharrou effectiveforecastingofkeyfeaturesinhospitalemergencydepartmenthybriddeeplearningdrivenmethods AT abdelkaderdairi effectiveforecastingofkeyfeaturesinhospitalemergencydepartmenthybriddeeplearningdrivenmethods AT faridkadri effectiveforecastingofkeyfeaturesinhospitalemergencydepartmenthybriddeeplearningdrivenmethods AT yingsun effectiveforecastingofkeyfeaturesinhospitalemergencydepartmenthybriddeeplearningdrivenmethods
_version_	1718418154302996480

Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods

Ejemplares similares