1. Automated healthcare-associated infection surveillance using an artificial intelligence algorithm
- Author
-
Camila Hubner Dalmora, R.P. dos Santos, Tiago Andres Vaz, A. Menezes, Otávio Luiz da Fontoura Carvalho, R. Pozza, Diandra Caroline Martins e Silva, N. Golin, J. Giacomazzi, and S. Lukasewicz
- Subjects
Healthcare associated infections ,Infection surveillance ,Artificial intelligence ,animal structures ,Receiver operating characteristic ,business.industry ,Short Report ,virus diseases ,Infectious and parasitic diseases ,RC109-216 ,Medicine ,Infection control ,Sensitivity (control systems) ,Public aspects of medicine ,RA1-1270 ,Healthcare-associated infection ,business ,Algorithm ,Cohort study ,Multilayer perceptron neural network - Abstract
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.
- Published
- 2021