Automated healthcare-associated infection surveillance using an artificial intelligence algorithm

• Main Authors: R.P. dos Santos (Author), D. Silva (Author), A. Menezes (Author), S. Lukasewicz (Author), C.H. Dalmora (Author), O. Carvalho (Author), J. Giacomazzi (Author), N. Golin (Author), R. Pozza (Author), T.A. Vaz (Author)
• Format: Book
• Published: Elsevier, 2021-09-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.
• Notes: 2590-0889; 10.1016/j.infpip.2021.100167
• Keywords: Infection surveillance; Artificial intelligence; Healthcare-associated infection; Infectious and parasitic diseases; RC109-216; Public aspects of medicine; RA1-1270
• Source: Infection Prevention in Practice, Vol 3, Iss 3, Pp 100167- (2021)

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.