Analysis of the open database of the General Directorate of Epidemiology using Deep Learning to predict the need for intubation in patients hospitalized for COVID-19

Authors

  • Omar Fabián Rivera Ceniceros Universidad Politécnica de Durango
  • Luis Alberto Ordaz Díaz Universidad Politécnica de Durango

DOI:

https://doi.org/10.37636/recit.v43195207

Keywords:

COVID-19, Deep learning, Sequential neural network

Abstract

Using deep learning, the aim is to determine the possibility that a patient hospitalized by COVID-19 suffers from respiratory failure and needs to be mechanically ventilated in a medical intensive care unit (ICU). The deep analysis is performed by training the Sequential Neural Networks algorithm, since these present good efficiency in the analysis of open data. For this study, the open database of the General Directorate of Epidemiology was used. According to the official decrees of the federation, the historical databases and the information related to the cases associated with COVID-19 are of free use with the purpose of facilitating access, use, reuse and redistribution to all users who require it. The database of the General Directorate of Epidemiology presents various information that, according to an interview with a first-line doctor who works with COVID-19 patients and in his opinion, some data may be irrelevant, as the nationality of people infected, to mention a few; likewise, we worked only with those patients who tested positive for the disease. In the same way, the database can be used to find some other aspects or relevant statistical data about the COVID-19 pandemic in México.

Downloads

Download data is not yet available.

Author Biography

Luis Alberto Ordaz Díaz, Universidad Politécnica de Durango

Profesor investigador de tiempo completo en la Universidad Politécnica de Durango, pertenece al Sistema Nacional de Investigadores (SNI) Nivel 1. 

References

Dirección general de Epidemiologia. Datos Abiertos Dirección General de Epidemiología, Internet: https://www.gob.mx/salud/documentos/datos-abiertos-152127 [7, enero, 2021].

J. Pearce. (2020, Abril). "A Review of Open-Source Ventilators For COVID-19 And Future Pandemics,". F1000Research, 9:218. Disponible https://doi.org/10.12688/f1000research.22942.2, [Feb. 12, 2021].

E. Tse, D. Klug y M. Todd. (2020, Oct.). "Open science approaches to COVID-19," F1000Research, 9:1043. Disponible: https://doi.org/10.12688/f1000research.26084.1, [Feb. 13,2020].

A.Väänänen, K. Haataja, K. Vehviläinen-Julkunen y P. Toivanen. (2021, Marzo). "Proposal of a novel Artificial Intelligence Distribution Service platform for healthcare," F1000Research, 10:245. Disponible: https://doi.org/10.12688/f1000research.36775.1 [Abril 8, 2021].

C. Castillo, C. Valdivia, C. Osorio et al. (2021, Enero). 4th ISCB Latin American Student Council Symposium: "A virtual and inclusive experience during COVID-19 times," F1000Research, 9:1460, Disponible: https://doi.org/10.12688/f1000research.28330.1 [Abril 15, 2021].

M. Capistran, A. Capella, J. Christen (2020, Junio). "Forecasting hospital demand during COVID-19 pandemic outbreaks," arXiv:2006.01873, Disponible: https://arxiv.org/abs/2006.01873 [Enero 20, 2021].

J. Rao, H. Zhang y A. Mantero. (2020, Mayo). "Contextualizing COVID-19 spread: a county level analysis, urban versus rural, and implications for preparing for the next wave". F1000Research, 9:418. Disponible: https://doi.org/10.12688/f1000research.23903.1 [Abril 15, 2021].

R. Sierra. "Índice de vulnerabilidad municipal a COVID-19," CONABIO, CIMAT. Guanajuato. Reporte Técnico, Núm. 2, 14 de julio de 2020 [Abril 19, 2021].

R. Casado. "Respiradores frente al COVID-19: Diferentes tipos para cada situación.". Revista EFE:SALUD, 24 de Abril de 2020 [Abril 19, 2021].

RGT consultores. "El Sistema Respiratorio y el COVID-19", Internet: https://rgtconsultores.mx/blog/el-sistema-respiratorio-y-el-COVID-19-parte-1, 12 de mayo de 2020 [Diciembre 20, 2020].

RGT consultores. "Ventiladores Mecánicos ante el COVID-19", Internet: https://rgtconsultores.mx/blog/ventiladores-mecanicos-ante-el-COVID-19, 20 de mayo de 2020 [Diciembre 20, 2020].

R, Ortiz, (2020, Oct.). "Análisis métrico de la producción científica sobre COVID-19 en SCOPUS". Revista Cubana de Información en Ciencias de la Salud, vol.31 no.3 e1587. Epub 30 de octubre de 2020. Disponible: http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S2307-21132020000300002&lng=es&tlng=es. [Diciembre 17. 2020].

J, VanderPlas. "Python Data Science Handbook ". O'Reilly Media, Inc., 2015, 1005 Gravenstein Highway North, Sebastopol, CA 95472. pp. 331-332, 359-462.

A. Gulli, P. Sujit. "Deep Learning with Keras". Packt Publishing Ltd, 2017, Livery Place, 35 Livery Street, Birmingham, UK. pp. 368-422.

M. Rodríguez. "COVID-19: ¿es el sistema inmunológico de las mujeres más robusto que el de los hombres? (y los interesantes hallazgos que se están dando por el coronavirus)". Internet: https://www.bbc.com/mundo/noticias-54344789. Octubre 2020, [Mayo 17, 2021].

F. Petite, M. Rivera, J. San Miguel, Y. Malo., J. Flores, M. Cuartero (Abril 9, 2021). Initial findings in chest X-rays as predictors of worsening lung infection in patients with COVID-19: correlation in 265 patients. Radiology, S0033-8338(21)00081-3. Elsevier Public Health Emergency Collection. Advance online publication. https://doi.org/10.1016/j.rx.2021.03.004, [Mayo 17, 2021].

List of COVID-19 patients and their possibility of being intubated.

Published

2021-09-10

How to Cite

Rivera Ceniceros, O. F., & Ordaz Díaz, L. A. (2021). Analysis of the open database of the General Directorate of Epidemiology using Deep Learning to predict the need for intubation in patients hospitalized for COVID-19. Revista De Ciencias Tecnológicas, 4(3), 195–207. https://doi.org/10.37636/recit.v43195207

Issue

Section

Research articles