Artificial Intelligence Technologies in Nursing Clinical Decision-Making: An Umbrella Review.
Robyn Cant, Colleen Ryan, Ritesh Chugh
PMID 41841218WHAT IT FOUND
Most AI tools for nurses were still being developed or tested; only 7% reported real-world benefit, though studies explored delirium, falls, triage and monitoring.
Key findings
01Most AI studies in the included reviews were at development or testing stage, and only 7% reported actual benefits.
02Random forest was reported as the most frequently used or most accurate machine learning method in several reviews.
03In one meta-analysis, delirium prediction models had sensitivity 0.85 and specificity 0.80, but most studies had high risk of bias and missing data.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
No formal quality assessment was conducted because umbrella reviews have no recognised standard. Most primary studies were descriptive or cohort designs, with few controlled or randomised comparisons. Many AI applications were only developed or tested, with limited use by nurses in real settings. Heterogeneity, incomplete reporting and missing data made studies difficult to compare. The search was English-only and limited to 2019 to 2024, so relevant reviews may have been missed.
Declared interests
The authors reported nothing to report for funding and declared no conflicts of interest.
The easy way to misread this
Do not conclude that AI improves nursing decisions or patient care. Most studies were development or testing, and only 7% reported actual benefits.