Artificial Intelligence as a Bridge to Gaps in Delirium Prediction, Detection, and Management
Journal of the American Geriatrics Society · 05.11.2026
DOI: 10.1111/jgs.70823 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Geriatrics Society, online erschienen am 05.11.2026. Verfasst von Sandeep R Pagali und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA. Die Arbeit nennt 30 Literaturangaben. Gefördert von: NIH HHS, Center for Artificial Intelligence Research/EAI, Robert and Arlene Kogod Center on Aging.
Abstract (Originalsprache)
Background
Delirium affects up to one‐third of hospitalized older adults and is associated with adverse outcomes. Despite its clinical importance and the availability of validated screening tools, current care gaps extend beyond under‐recognition to inconsistent risk stratification, workforce constraints, documentation burden, fragmented intervention delivery, and practical challenges with monitoring of response. We review how artificial intelligence (AI) could bridge these gaps and distinguish model development and validation, real‐world clinical implementation, and emerging concepts in delirium care.
Results
Prediction models leveraging multimodal health record data, including structured variables and unstructured clinical notes, report good discrimination for delirium risk stratification, but only a few models have been integrated into clinical practice. A live multimodal machine learning model increased targeted delirium detection, yet a pre‐post comparative study found a longer length of stay; improved recognition alone therefore does not equate with improved outcomes. Natural language processing, large language models, computer vision, ambient sensing, and wearable technologies enable more continuous, objective, and less labor‐intensive assessment compared with traditional screening methods, but evidence remains limited with concerns about false positives and generalizability. AI‐supported delirium management through reinforcement learning and digital twins is currently largely conceptual. Responsible AI adoption requires a clearly defined intended use, external validation, action pathways, equitable performance, privacy and security, consent and transparency, clinician oversight, patient preferences, and post‐deployment monitoring.
Conclusion
AI is most defensible as an adjunct that connects evidence‐based delirium care to reliable execution rather than as a replacement for clinical assessment. Prospective comparative studies should evaluate patient outcomes, resource use, and balancing measures.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA.
- Aurora UW Medical Group, Milwaukee, Wisconsin, USA.
- Department of Clinical and Health Informatics, UT Health Houston, Houston, Texas, USA.
- Division of Geriatric Medicine and Gerontology, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
- Division of Geriatric and Palliative Medicine, UT Health Houston, Houston, Texas, USA.
- Division of Nursing Research, Mayo Clinic, Rochester, Minnesota, USA.
ORCID-Profile: Sandeep R Pagali, Sunyang Fu, Mfon E Umoh, Minji Kwak, Heidi Lindroth, Tru Brynes, Marie Pavini
Förderung
- NIH HHS
- Center for Artificial Intelligence Research/EAI
- Robert and Arlene Kogod Center on Aging
- NIA NIH HHS
- NCATS NIH HHS
- National Center for Advancing Translational Sciences
- National Institutes of Health
Zitieren
APA
Pagali, S. R., Khan, A., Fu, S., Umoh, M. E., Kwak, M., Lindroth, H., Brynes, T., Magnabosco, L., Karol, D., Pavini, M., Oh, E. S., & American Delirium Society Innovation in Delirium Special Interest Group (2026). Artificial Intelligence as a Bridge to Gaps in Delirium Prediction, Detection, and Management. Journal of the American Geriatrics Society. https://doi.org/10.1111/jgs.70823
Vancouver
Pagali SR, Khan A, Fu S, Umoh ME, Kwak M, Lindroth H, et al. Artificial Intelligence as a Bridge to Gaps in Delirium Prediction, Detection, and Management. Journal of the American Geriatrics Society. 2026. doi:10.1111/jgs.70823
BibTeX
@article{Pagali2026,
author = {Pagali, Sandeep R and Khan, Ariba and Fu, Sunyang and Umoh, Mfon E and Kwak, Minji and Lindroth, Heidi and Brynes, Tru and Magnabosco, Lara and Karol, David and Pavini, Marie and Oh, Esther S and American Delirium Society Innovation in Delirium Special Interest Group, American Delirium Society Innovation in Delirium Special Interest Group},
title = {Artificial Intelligence as a Bridge to Gaps in Delirium Prediction, Detection, and Management},
journal = {Journal of the American Geriatrics Society},
year = {2026},
doi = {10.1111/jgs.70823}
}
EUVIMED