dc.contributor | Aya Parra, Pedro Antonio | |
dc.creator | Gracia Ramírez, David Leonardo | |
dc.date.accessioned | 2022-10-05T17:10:16Z | |
dc.date.accessioned | 2023-09-06T21:16:59Z | |
dc.date.available | 2022-10-05T17:10:16Z | |
dc.date.available | 2023-09-06T21:16:59Z | |
dc.date.created | 2022-10-05T17:10:16Z | |
dc.date.issued | 2022 | |
dc.identifier | https://repositorio.escuelaing.edu.co/handle/001/2132 | |
dc.identifier | https://catalogo.escuelaing.edu.co/cgi-bin/koha/opac-detail.pl?biblionumber=23192 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8707250 | |
dc.description.abstract | El presente documento es el resultado de la investigación de fallas comunes en máquina de anestesia realizada en un hospital de cuarto nivel en la ciudad de Bogotá. Además, se encuentra la metodología que se realizó para el desarrollo del algoritmo de identificación de fallas a partir de los datos de los mantenimientos correctivos recolectados en el hospital de los fabricantes Dräger y Datex Ohmeda por medio de dos métodos de Machine Learning. Obteniendo como resultado para la identificación de fallas en máquinas de anestesia de marca Dräger el método con mayor precisión fue el Decision Tree Classifier con un 76% de certeza. Mientras que para Datex Ohmeda el método con mayor precisión fue Random Forest Classifier con el 74,4% de efectividad. | |
dc.description.abstract | This document is the result of the investigation of common failures in anesthesia machines carried out in a fourth level hospital in the city of Bogotá. In addition, there is the methodology that was carried out for the development of the fault identification algorithm from the corrective maintenance data collected in the hospital from the manufacturers Dräger and Datex Ohmeda through two Machine Learning methods. Obtaining as a result for the identification of failures in Dräger brand anesthesia machines, the method with greater precision was the Decision Tree Classifier with 76% certainty. While for Datex Ohmeda the method with the highest accuracy was Random Forest Classifier with 74.4% effectiveness. | |
dc.language | spa | |
dc.publisher | Ingeniería Biomédica | |
dc.publisher | Ingeniería Biomédica | |
dc.relation | N/A | |
dc.relation | [1] “Anestesia general.” https://www.news-medical.net/health/General-Anesthesia-(Spanish).aspx (accessed Jan. 11, 2022). [2] “General anaesthesia - NHS.” https://www.nhs.uk/conditions/general-anaesthesia/ (accessed Jan. 11, 2022). [3] “Continuum of Depth of Sedation: Definition of General Anesthesia and Levels of Sedation/Analgesia | American Society of Anesthesiologists (ASA).” https://www.asahq.org/standards-and-guidelines/continuum-of-depth-of-sedation-definition-of-general-anesthesia-and-levels-of-sedationanalgesia (accessed Jan. 11, 2022). [4] L. G. Braz, D. G. Braz, D. S. da Cruz, L. A. Fernandes, N. S. P. Módolo, and J. R. C. Braz, “Mortality in anesthesia: a systematic review,” Clinics (Sao Paulo, Brazil), vol. 64, no. 10, pp. 999–1006, 2009, doi: 10.1590/S1807-59322009001000011. [5] R. J. AMOS, J. A. L. AMESS, D. G. NANCEKIEVILL, and G. M. REES, “PREVENTION OF NITROUS OXIDE-INDUCED MEGALOBLASTIC CHANGES IN BONE MARROW USING FOLINIC ACID,” BJA: British Journal of Anaesthesia, vol. 56, no. 2, pp. 103–1 | |
dc.rights | info:eu-repo/semantics/openAccess | |
dc.title | Desarrollo de algoritmo para el apoyo en la identificación de fallas comunes en máquinas de anestesia | |
dc.type | Trabajo de grado - Pregrado | |