Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
Summary: 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 percep...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | Infection Prevention in Practice |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590088921000561 |
| _version_ | 1818437676605374464 |
|---|---|
| author | R.P. dos Santos D. Silva A. Menezes S. Lukasewicz C.H. Dalmora O. Carvalho J. Giacomazzi N. Golin R. Pozza T.A. Vaz |
| author_facet | R.P. dos Santos D. Silva A. Menezes S. Lukasewicz C.H. Dalmora O. Carvalho J. Giacomazzi N. Golin R. Pozza T.A. Vaz |
| author_sort | R.P. dos Santos |
| collection | DOAJ |
| description | Summary: 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. |
| first_indexed | 2024-12-14T17:28:28Z |
| format | Article |
| id | doaj.art-c0c004c5d2b44be2ac2175f7f07e1f6c |
| institution | Directory Open Access Journal |
| issn | 2590-0889 |
| language | English |
| last_indexed | 2024-12-14T17:28:28Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Infection Prevention in Practice |
| spelling | doaj.art-c0c004c5d2b44be2ac2175f7f07e1f6c2022-12-21T22:53:10ZengElsevierInfection Prevention in Practice2590-08892021-09-0133100167Automated healthcare-associated infection surveillance using an artificial intelligence algorithmR.P. dos Santos0D. Silva1A. Menezes2S. Lukasewicz3C.H. Dalmora4O. Carvalho5J. Giacomazzi6N. Golin7R. Pozza8T.A. Vaz9Qualis Soluções em Infectologia, BrazilQualis Soluções em Infectologia, Brazil; Corresponding author. Address: Rodrigo Pires dos Santos, Oswaldo Aranha, 1022, Room 1101, Porto Alegre, RS. 90035-191, Brazil.Qualis Soluções em Infectologia, BrazilQualis Soluções em Infectologia, BrazilQualis Soluções em Infectologia, BrazilQualis Soluções em Infectologia, BrazilHospital Tacchini, BrazilHospital Tacchini, BrazilHospital Tacchini, BrazilQualis Soluções em Infectologia, BrazilSummary: 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.http://www.sciencedirect.com/science/article/pii/S2590088921000561Infection surveillanceArtificial intelligenceHealthcare-associated infection |
| spellingShingle | R.P. dos Santos D. Silva A. Menezes S. Lukasewicz C.H. Dalmora O. Carvalho J. Giacomazzi N. Golin R. Pozza T.A. Vaz Automated healthcare-associated infection surveillance using an artificial intelligence algorithm Infection Prevention in Practice Infection surveillance Artificial intelligence Healthcare-associated infection |
| 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 | Infection surveillance Artificial intelligence Healthcare-associated infection |
| url | http://www.sciencedirect.com/science/article/pii/S2590088921000561 |
| work_keys_str_mv | AT rpdossantos automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT dsilva automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT amenezes automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT slukasewicz automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT chdalmora automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT ocarvalho automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT jgiacomazzi automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT ngolin automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT rpozza automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm AT tavaz automatedhealthcareassociatedinfectionsurveillanceusinganartificialintelligencealgorithm |