Harnessing Artificial Intelligence to Strengthen Acute and Critical Care Nursing Practice: A Systematic Review
Item Type: Journal Article
Authors: Almagharbeh, Wesam Taher;Alkubati, Sameer A.;Alasmari, Amal Ali;Alharbi, Amal Ali;Alfanash, Hazem AbdulKareem;Abuadas, Fuad H.;El Arab, Rabie Adel;Alkhawaldeh, Abdullah;Alamri, Ayman Ateq;Albalawi, Haia Mahdi and Alatawi, Abeer
Publication Date: 2026
Journal: Nursing in Critical Care 31(5), pp. e70606
Abstract:
Background Artificial intelligence (AI) is reshaping clinical
decision support systems (CDSSs). In acute and critical care, nurses provide
continuous surveillance, recognise deterioration, coordinate escalation and
translate protocols into bedside action. AI-CDSS may be particularly relevant
when they support rather than replace clinical judgement. Aim To examine
whether nurse-used AI-CDSS improve patient-important outcomes in acute and
critical care contexts and summarise effects on care processes and nurse-reported
outcomes.
Study Design Following PRISMA 2020 and a preregistered protocol, we
searched eight databases and major trial registries for English-language
studies from 1 January 2010 to 1 January 2026. Searches were conducted on 1
January 2026. We included randomised, quasi-experimental and adjusted cohort
studies in which registered nurses or nursing teams were primary users of
AI-CDSS generating patient-specific predictions or recommendations. Mortality
was pooled using a random effects model; other outcomes were synthesised
narratively.
Results Seven studies involving about 75 000 patients were
included. Most evidence came from acute wards, intensive care units, sepsis,
deterioration and delirium-prevention contexts, with additional home and palliative
care evidence. Three mortality studies were pooled. Nurse-facing AI-CDSS were
associated with lower hospital mortality (RR 0.68, 95% CI 0.53-0.87; I2
= 24%), although the prediction interval included possible no effect. Length of
stay and protocol adherence generally improved when tools were embedded in
nursing workflows. Nurse-reported outcomes were sparse.
Conclusion Nurse-facing
AI-CDSS may strengthen acute and critical care nursing by improving
surveillance, escalation and protocol delivery for patients at risk of
deterioration. Evidence is promising but limited by small study numbers,
heterogeneous interventions and sparse nurse-reported outcomes. Critical care
implementation should prioritise nurse-centred design, alert burden, equity,
safety monitoring and rigorous evaluation before scale-up. Relevance to
Clinical Practice Nurse-used AI-CDSS show potential to improve patient outcomes
and care processes, but evidence remains limited and context dependent.
Access or request full text: https://libkey.io/10.1111/nicc.70606
Access or request full text: https://libkey.io/10.1111/nicc.70606
No comments:
Post a Comment