Citations

ABSTRACT 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.

ABSTRACT Background Delirium predicts adverse outcomes in older emergency department (ED) patients, but many acutely ill patients without delirium have underlying cognitive impairment that goes unrecognized. Whether cognitive impairment screening improves risk prediction beyond delirium remains uncertain. We compared practical bedside screening strategies for delirium, cognitive impairment, or both for predicting 90‐day functional decline and mortality in older adults admitted from the ED. Methods A prospective cohort comprising patients aged ≥ 65 years admitted from the ED of a large hospital in São Paulo, Brazil. Trained professionals screened for delirium using the brief Confusion Assessment Method (bCAM) and for cognitive impairment using the 10‐point Cognitive Screener (10‐CS). Patients were classified as having normal cognition (bCAM negative, 10‐CS > 5), delirium (bCAM positive), or cognitive impairment without delirium (bCAM negative, 10‐CS ≤ 5). Blinded investigators assessed decline in basic activities of daily living (ADL) and mortality within 90 days of admission. Fine‐Gray models (death as a competing risk) and Cox models estimated associations with outcomes, adjusting for sociodemographic and clinical factors. Results Among 830 patients (mean age = 80 ± 9 years; women = 47%), 427 (51.5%) had normal cognition, 171 (20.6%) had delirium, and 232 (27.9%) had cognitive impairment without delirium. Among delirium‐negative patients with cognitive impairment, 52% had no documented dementia diagnosis or reported memory problems. Compared with normal cognition, cognitive impairment without delirium was associated with 90‐day functional ADL decline (sub‐HR = 1.60; 95% CI = 1.03–2.49) and mortality (HR = 2.31; 95% CI = 1.18–4.51), with risks similar to those observed in delirium. A staged strategy (bCAM first, then 10‐CS if bCAM negative) showed higher discrimination than delirium‐only or 10‐CS‐only screening. Conclusions Cognitive impairment without delirium is common, often unrecognized, and predicts 90‐day adverse outcomes in older patients admitted from the ED. A brief staged screening strategy integrating delirium assessment with cognitive impairment testing among delirium‐negative patients may enhance early detection of cognitive vulnerability and support care planning.