Selection of the influential factors in the prediction of hospital beds in a health institution of high complexity level, through the use of artificial neural networks
DOI:
https://doi.org/10.17081/innosa.79Keywords:
Multilayer Perceptron, Models, Artificial Neural Networks, Hospital BedsAbstract
Background: In the context of any hospital institution, health administrators focus their efforts on knowing the future state of their areas, in order to minimize risks and make better decisions. Currently, organizations have focused on understanding and giving value to the data generated within their processes, through the use of optimization models and computational tools, in order to convert them into valuable information and find optimal and competitive solutions. Methods: 5 indicators were analyzed in a monthly institution. These were collected through files obtained in Microsoft EXCEL-2016 format from January 2004 to December 2018, later, 3 Multilayer Perceptron RNAs were modeled with the help of IBM SPSS version 19 software. Results: It is shown by the RNA that demand is the most important variable for the prediction of hospital beds, this with an importance of 63%, 45% and 51% for each RNA. Similarly, model 1 is presented with the most successful. On the other hand, the average length of stay is the least important variable to forecast. Conclusions: Through this study it was possible to show that the institution should give greater importance to factors such as demand and the bed spin indicator. These must be constantly managed within the administrative work of the institution.
Downloads
References
Iqbal R, Doctor F, More B , Mahmud S, Yousuf U. Big data analytics: Computational intelligence techniques and application areas. Technol. Forecast. Soc. Change, no. December 2017, pp. 0–1, 2018. DOI: 10.1016/j.techfore.2018.03.024
Mejía D, Toro E. Pronóstico de ventas usando redes neuronales. Sci. Tech., vol. 10, no. 26, pp. 25–30, 2004. DOI: 10.22517/23447214.7047
Blanco A, Pino-Mejías R, Lara J, Rayo S. Credit scoring models for the microfinance industry using neural networks: Evidence from Peru. Expert Syst. Appl., vol. 40, no. 1, pp. 356–364, 2013. DOI: 10.1016/j.eswa.2012.07.051
Pitarque A, Ruiz J, Roy J. Las redes neuronales como herramientas estadísticas no paramétricas de clasificación. Psicothema, vol. 12, no. SUPPL. 2, pp. 459–463, 2000. Disponible en: http://www.psicothema.com/pdf/604.pdf
Geem Z , Roper W. Energy demand estimation of South Korea using artificial neural network. Energy Policy, vol. 37, no. 10, pp. 4049–4054, 2009. DOI: 10.1016/j.enpol.2009.04.049
Xiang X, Deng Y. Second order spiking perceptron and its applications. Appl. Math. Model., vol. 34, no. 10, pp. 2966–2980, 2010. DOI 10.1016/j.apm.2010.01.006
Lacson R, Ohno-Machado L. Artificial Neural Networks in Encyclopedia of Medical Decision Making M. W. Kattan, Ed. 2455 Teller Road, Thousand Oaks California 91320 United States: SAGE Publications, Inc., 2009, p. 9
Kigami J. Mathematical Background. 2001, pp. 196–211.
Bansal D, Chhikara R, Khanna K, Gupta P. Comparative Analysis of Various Machine Learning Algorithms for Detecting Dementia. Procedia Comput. Sci., vol. 132, pp. 1497–1502, 2018. DOI: 10.1016/j.procs.2018.05.102
Serrano-Cinca C. Self organizing neural networks for financial diagnosis. Decis. Support Syst., vol. 17, no. 3, pp. 227–238, 1996. DOI: 10.1016/0167-9236(95)00033-X
Leshno M, Y. Spector Y. Neural network prediction analysis: The bankruptcy case. Neurocomputing, vol. 10, no. 2, pp. 125–147, 1996. DOI 10.1016/0925-2312(94)00060-3
Kuzey C, Uyar A, Delen D. The impact of multinationality on firm value: A comparative analysis of machine learning techniques. Decis. Support Syst., vol. 59, no. 1, pp. 127–142, 2014. DOI: 10.1016/j.dss.2013.11.001
Lao O, Caridad M. Procedimiento para el pronóstico de la demanda mediante redes neuronales artificiales. Ciencias Holguín, vol. 23, no. 1, pp. 1–18, 2017. Disponible en: http://www.ciencias.holguin.cu/index.php/cienciasholguin/article/view/995/1097
Rajendra P, Manash E. Deep learning: A branch of machine learning. J. Phys. Conf. Ser., vol. 1228, no. 1, 2019. Disponible en: https://iopscience.iop.org/article/10.1088/1742-6596/1228/1/012045/meta
Hamadache M, Benkortbi O, Hanini S, Amrane A. Application of multilayer perceptron for prediction of the rat acute toxicity of insecticides. Energy Procedia, vol. 139, pp. 37–42, 2017. DOI 10.1016/j.egypro.2017.11.169
Baum E. On the capabilities of multilayer perceptrons. J. Complex., vol. 4, no. 3, pp. 193–215, 1988. DOI: 10.1016/0885-064X(88)90020-9
Gómez O, Garcés L. Inferencia estadísitica utilizando redes neuronales artificiales. Sci. Tech., vol. 5, no. 26, pp. 31–36, 2004. Disponible en: https://revistas.utp.edu.co/index.php/revistaciencia/article/view/7049
Arroyo I. Evaluación de dos técnicas de reconocimiento de patrones para su implementación en el simulador de pilotaje automatico de taller del STC metro de la ciudad de méxico. Universidad tecnológica de la Mixteca, 2013. Disponible en: https://www.academia.edu/16113248/Evaluaci%C3%B3n_de_dos_t%C3%A9cnicas_de_reconocimiento_de_patrones_para_su_implementaci%C3%B3n_en_el_Simulador_de_pilotaje_autom%C3%A1tico_de_taller_del_STC_Metro_de_la_Cd._de_M%C3%A9xico
Cabaneros S, Calautit J, Hughes B. Hybrid Artificial Neural Network Models for Effective Prediction and Mitigation of Urban Roadside NO2Pollution. Energy Procedia, vol. 142, pp. 3524–3530, 2017. DOI: 10.1016/j.egypro.2017.12.240
Hanafizadeh P, Ravasan A, Khaki H. An expert system for perfume selection using artificial neural network. Expert Syst. Appl., vol. 37, no. 12, pp. 8879–8887, 2010. DOI: 10.1016/j.eswa.2010.06.008
Kengpol A, Wangananon W. The expert system for assessing customer satisfaction on fragrance notes: Using artificial neural networks. Comput. Ind. Eng., vol. 51, no. 4, pp. 567–584, 2006. DOI: 10.1016/j.cie.2006.04.006
Michalak K, Kwaśnicka H. Influence of data dimensionality on the quality of forecasts given by a multilayer perceptron. Theor. Comput. Sci., vol. 371, no. 1–2, pp. 62–71, 2007. DOI: 10.1016/j.tcs.2006.10.014
Galeshchuk S. Neural networks performance in exchange rate prediction. Neurocomputing, vol. 172, pp. 446–452, 2016. DOI: 10.1016/j.neucom.2015.03.100
Hernández-Orallo J. ROC curves for regression. Pattern Recognit., vol. 46, no. 12, pp. 3395–3411, 2013. DOI: 10.1016/j.patcog.2013.06.014
Dominguez E, Gonzalez R. Análisis de las curvas Receiver Operating Characteristic: un método útil para evaluar procederes diagnósticos. 2002. Disponible en: http://scielo.sld.cu/scielo.php?script=sci_abstract&pid=S1561-29532002000200010&lng=es&nrm=iso&tlng=es
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Julián Alberto Uribe Gómez, Juan Guillermo Barrientos Gómez
This work is licensed under a Creative Commons Attribution 4.0 International License.
