Automated healthcare-associated infection surveillance using an artificial intelligence algorithm

Healthcare-associated infections (HAIs) are among the most common adverse events in hospitals. We used artificial intelligence (AI) algorithms for infection surveillance in a cohort study. The model correctly detected 67 out of 73 patients with HAIs. The final model used a multilayer perceptron neur...

Descripción completa

Detalles Bibliográficos
Autores principales: dos Santos, R.P., Silva, D., Menezes, A., Lukasewicz, S., Dalmora, C.H., Carvalho, O., Giacomazzi, J., Golin, N., Pozza, R., Vaz, T.A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2021
Materias:
Short Report
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8387762/
https://www.ncbi.nlm.nih.gov/pubmed/34471868
http://dx.doi.org/10.1016/j.infpip.2021.100167
_version_ 1783742509196771328
author dos Santos, R.P.
Silva, D.
Menezes, A.
Lukasewicz, S.
Dalmora, C.H.
Carvalho, O.
Giacomazzi, J.
Golin, N.
Pozza, R.
Vaz, T.A.
author_facet dos Santos, R.P.
Silva, D.
Menezes, A.
Lukasewicz, S.
Dalmora, C.H.
Carvalho, O.
Giacomazzi, J.
Golin, N.
Pozza, R.
Vaz, T.A.
author_sort dos Santos, R.P.
collection PubMed
description Healthcare-associated infections (HAIs) are among the most common adverse events in hospitals. We used artificial intelligence (AI) algorithms for infection surveillance in a cohort study. The model correctly detected 67 out of 73 patients with HAIs. The final model used a multilayer perceptron neural network achieving an area under receiver operating curve (AUROC) of 90.27%; specificity of 78.86%; sensitivity of 88.57%. Respiratory infections had the best results (AUROC ≥93.47%). The AI algorithm could identify most HAIs. AI is a feasible method for HAI surveillance, has the potential to save time, promote accurate hospital-wide surveillance, and improve infection prevention performance.
format Online
Article
Text
id pubmed-8387762
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-83877622021-08-31 Automated healthcare-associated infection surveillance using an artificial intelligence algorithm dos Santos, R.P. Silva, D. Menezes, A. Lukasewicz, S. Dalmora, C.H. Carvalho, O. Giacomazzi, J. Golin, N. Pozza, R. Vaz, T.A. Infect Prev Pract Short Report Healthcare-associated infections (HAIs) are among the most common adverse events in hospitals. We used artificial intelligence (AI) algorithms for infection surveillance in a cohort study. The model correctly detected 67 out of 73 patients with HAIs. The final model used a multilayer perceptron neural network achieving an area under receiver operating curve (AUROC) of 90.27%; specificity of 78.86%; sensitivity of 88.57%. Respiratory infections had the best results (AUROC ≥93.47%). The AI algorithm could identify most HAIs. AI is a feasible method for HAI surveillance, has the potential to save time, promote accurate hospital-wide surveillance, and improve infection prevention performance. Elsevier 2021-07-31 /pmc/articles/PMC8387762/ /pubmed/34471868 http://dx.doi.org/10.1016/j.infpip.2021.100167 Text en © 2021 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Short Report
dos Santos, R.P.
Silva, D.
Menezes, A.
Lukasewicz, S.
Dalmora, C.H.
Carvalho, O.
Giacomazzi, J.
Golin, N.
Pozza, R.
Vaz, T.A.
Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title_full Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title_fullStr Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title_full_unstemmed Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title_short Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
title_sort automated healthcare-associated infection surveillance using an artificial intelligence algorithm
topic Short Report
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8387762/
https://www.ncbi.nlm.nih.gov/pubmed/34471868
http://dx.doi.org/10.1016/j.infpip.2021.100167
work_keys_str_mv AT dossantosrp automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT silvad automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT menezesa automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT lukasewiczs automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT dalmorach automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT carvalhoo automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT giacomazzij automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT golinn automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT pozzar automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm
AT vazta automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm

Ejemplares similares