Data-Driven Quality of Care in the ICU: A Concise Review
AI and ML have the potential to transform ICU management. However, their success depends on validated methodologies, interoperable data frameworks, and interpretable models that clinicians can trust. Advancing AI use in the ICU demands a multidisciplinary effort to create adaptive, transparent, and clinically meaningful solutions that enhance patient care and improve workflow, while ensuring safety and efficiency.
Authors
- G. M. Moralez (ORCID: https://orcid.org/0000-0002-3780-4008)
- Sing Chee Tan (ORCID: https://orcid.org/0000-0002-5301-5914)
- Geert Meyfroidt (ORCID: https://orcid.org/0000-0003-4259-3935)
- Vincent X. Liu (ORCID: https://orcid.org/0000-0001-6899-9998)
- Jorge I. Salluh (ORCID: https://orcid.org/0000-0002-8164-1453)
- Filipe Amado (ORCID: https://orcid.org/0009-0006-5091-4072)
- David Pilcher
- Robert D. Stevens
Institutions
- Universidade Federal do Rio de Janeiro (BR)
- Kaiser Permanente (US)
- Johns Hopkins University (US)
- Northern Health (AU)
- Johns Hopkins Medicine (US)
- Australian and New Zealand Intensive Care Society (AU)
- D’Or Institute for Research and Education (BR)
- Alfred Health (AU)
- Universidade Nova de Lisboa (PT)
- KU Leuven (BE)
Publication Details
- Journal
- Critical Care Medicine
- Published
- 2025-09-19
- DOI
- https://doi.org/10.1097/ccm.0000000000006862
- Citations
- 3
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 7.44