Skip to content
Review Open access

The role of artificial intelligence for patient monitoring in the intensive care unit: a review of algorithms for predicting and analysing complications

Oct 2026 · Messenger of Anesthesiology and Resuscitation · 0 citations · 46 references

Abstract

The objective was to review current evidence on the use of artificial intelligence for patient monitoring in the intensive care unit, with a focus on early detection, prediction, and interpretation of major complications. Materials and methods. A narrative analytical review was conducted in accordance with SANRA principles. PubMed/MEDLINE, Scopus, Web of Science, and eLibrary.RU were searched for publications from 2020 to 2026. Systematic reviews, meta-analyses, and original studies addressing artificial intelligence algorithms in critical care monitoring and predicting complications were eligible for inclusion. Results . The most extensively investigated applications involved sepsis, acute kidney injury, delirium, in-hospital cardiac arrest, respiratory deterioration, and mortality. Early sepsis warning systems appear to be the most mature reaching an area under the receiver operating characteristic curve of 0.95 and low false-alarm rates. Gradient boosting methods, recurrent neural networks, and convolutional architectures frequently outperformed conventional severity scores in discrimination metrics. At the same time, most models remain limited to retrospective development and internal validation. Conclusion . Artificial intelligence algorithms have substantial potential for intensive care monitoring, yet clinical translation is still constrained by limited external validation, dataset heterogeneity, poor interpretability, and alarm fatigue. Practical implementation will require prospective multicentre studies, standardized reporting, and physician-led use of decision-support systems.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.