Infection Prevention in Practice (Sep 2021)

Automated healthcare-associated infection surveillance using an artificial intelligence algorithm

  • R.P. dos Santos,
  • D. Silva,
  • A. Menezes,
  • S. Lukasewicz,
  • C.H. Dalmora,
  • O. Carvalho,
  • J. Giacomazzi,
  • N. Golin,
  • R. Pozza,
  • T.A. Vaz

Journal volume & issue
Vol. 3, no. 3
p. 100167

Abstract

Read online

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.

Keywords