Artificial intelligence and computerized decision support in adult intensive care: A systematic review of randomized controlled trials
Authors' conclusion
AI and CDSS interventions in adult ICUs are associated with improvements in process-related outcomes but show limited and inconsistent effects on patient-centered endpoints.
Study context
- Population
- Adult ICU patients
- Participants
- ≈100,000 patients · 10 RCTs
- Comparison
- Artificial intelligence (AI)-based or clinical decision support systems (CDSS) interventions in adult intensive care units (ICUs)
- Outcome
- Process and patient-centred outcomes of AI-based or CDSS interventions in adult ICUs
Methodological detailsRoB 2 and CONSORT-AI quality assessment, Databases searched from inception to November 2025
- RoB 2 and CONSORT-AI quality assessment
- Databases searched from inception to November 2025
Pooled result
As reported in the abstract
Trials showing improvement in at least one process measure (earlier recognition of deterioration, improved protocol adherence, physiological stability)
8
Trials reporting reductions in mortality (a sepsis prediction model and a machine-learning-based early-warning system)
2
Further pooled results
Reporting of AI-specific elements
- Dataset provenance, algorithm versioning and human-AI interaction frequently incompletely reported
Original publication
Artificial intelligence and computerized decision support in adult intensive care: A systematic review of randomized controlled trials. J Crit Care. Published 27 April 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →