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
DOI:
https://doi.org/10.37636/recit.v43195207Keywords:
COVID-19, Deep learning, Sequential neural networkAbstract
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
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]. DOI: https://doi.org/10.12688/f1000research.22942.2
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]. DOI: https://doi.org/10.12688/f1000research.26084.1
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]. DOI: https://doi.org/10.12688/f1000research.36775.1
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]. DOI: https://doi.org/10.12688/f1000research.28330.1
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]. DOI: https://doi.org/10.12688/f1000research.23903.1
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]. DOI: https://doi.org/10.1016/j.rx.2021.03.004
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2021 Omar Fabián Rivera Ceniceros, Luis Alberto Ordaz Díaz
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors who publish in this journal accept the following conditions:
The authors retain the copyright and assign to the journal the right of the first publication, with the work registered with the Creative Commons Attribution license 4.0, which allows third parties to use what is published as long as they mention the authorship of the work and the first publication in this magazine.
Authors may make other independent and additional contractual agreements for the non-exclusive distribution of the version of the article published in this journal (eg, include it in an institutional repository or publish it in a book) as long as they clearly indicate that the work it was first published in this magazine.
Authors are allowed and encouraged to share their work online (for example: in institutional repositories or personal web pages) before and during the manuscript submission process, as it can lead to productive exchanges, greater and more quick citation of published work (see The Effect of Open Access).
