Characterizing and detecting delirium with clinical and computational measures of speech and language disturbance.

BACKGROUND: Delirium is a critically underdiagnosed syndrome of altered mental status affecting more than 50% of older adults admitted to hospital. Few studies have incorporated speech and language disturbance in delirium detection. We sought to describe speech and language disturbances in delirium, and provide a proof of concept for detecting delirium using computational speech and language features. METHODS: Participants underwent delirium assessment and completed language tasks. Speech and language disturbances were rated using standardized clinical scales. Recordings and transcripts were processed using an automated pipeline to extract acoustic and textual features. We used binomial, elastic net, machine learning models to predict delirium status. RESULTS: We included 33 older adults admitted to hospital, of whom 10 met criteria for delirium. The group with delirium scored higher on total language disturbances and incoherence, and lower on category fluency. Both groups scored lower on category fluency than the normative population. Cognitive dysfunction as a continuous measure was correlated with higher total language disturbance, incoherence, loss of goal and lower category fluency. Including computational language features in the model predicting delirium status increased accuracy to 78%. LIMITATIONS: This was a proof-of-concept study with limited sample size, without a set-aside cross-validation sample. Subsequent studies are needed before establishing a generalizable model for detecting delirium. CONCLUSION: Language impairments were elevated among patients with delirium and may also be used to identify subthreshold cognitive disturbances. Computational speech and language features are promising as accurate, noninvasive and efficient biomarkers of delirium.

Hospital practices and clinical outcomes associated with behavioral symptoms in persons with dementia.

BACKGROUND: Hospitalized persons living with dementia (PLWD) often experience behavioral symptoms that challenge medical care. OBJECTIVE: This study aimed to identify clinical practices and outcomes associated with behavioral symptoms in hospitalized PLWD. DESIGN: A retrospective cross-sectional study. SETTINGS AND PARTICIPANTS: The study included PLWD (65+) admitted to one of severe health system hospitals in 2019. INTERVENTION: Behavioral symptoms were defined as the presence of (1) a psychoactive medication for behavioral symptoms; (2) an order for physical restraints or constant observation; and/or (3) physician documentation of delirium, encephalopathy, or behavioral symptoms. MAIN OUTCOME AND MEASURES: Associations between behavioral symptoms and patient characteristics and hospital practices (e.g., bladder catheter) were examined. Multivariable logistic/linear regression was used to evaluate the association between behavioral symptoms and clinical outcomes (e.g., mortality). RESULTS: Of hospitalized PLWD (N = 8637), the average age was 84.5 years (IQR = 79-90), 61.7% were female, 60.1% were white, and 9.4% (n = 833) were Hispanic. Behavioral symptoms were identified in 40.6% (N = 3606) of individuals. Behavioral symptoms were significantly associated with male gender (40.3% vs. 36.9%, p = .001), white race (62.7% vs. 58.3%, p < .001), and residence in a facility prior to admission (26.6% vs. 23.7%, p < .001). Regarding hospital practices, indwelling bladder catheters (11.2% vs. 6.0%, p < .001) and dietary restriction (41.9% vs. 33.8%, p < .001) were associated with behavioral symptoms. In multivariable models, behavioral symptoms were associated with increased hospital mortality (odds ratio [OR]: 1.90, CI95%: 1.57-2.29), length of stay (parameter estimate: 2.10, p < .001), 30-day readmissions (OR: 1.14, CI95%: 1.014-1.289), and decreased discharge home (OR: 0.59, CI95%: 0.53-0.65, p < .001). CONCLUSIONS: Given the association between behavioral symptoms and poor clinical outcomes, there is an urgent need to improve the provision of care for hospitalized PLWD.