Automated healthcare-associated infection surveillance using an artificial intelligence algorithm. Issue 3 (September 2021)

• Record Type: Journal Article
• Authors: dos Santos, R.P.; Silva, D.; Menezes, A.; Lukasewicz, S.; Dalmora, C.H.; Carvalho, O.; Giacomazzi, J.; Golin, N.; Pozza, R.; Vaz, T.A.
• Is Part Of: Infection Prevention in Practice. Volume 3:Issue 3(2021)
• Publication Date: 2021-09
• Subjects: Infection surveillance -- Artificial intelligence -- Healthcare-associated infection; Infection -- Prevention -- Periodicals; Infection Control; Infection -- Prevention; Electronic journals; Periodical; Electronic journals; Periodicals; 616.9045
• DOI: 10.1016/j.infpip.2021.100167
• Languages: English
• ISSNs: 2590-0889

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.