Delirium screening in an acute care setting with a machine learning classifier based on routinely collected nursing data: A model development study.

Delirium screening in acute care settings is a resource intensive process with frequent deviations from screening protocols. A predictive model relying only on daily collected nursing data for delirium screening could expand the populations covered by such screening programs. Here, we present the results of the development and validation of a series of machine-learning based delirium prediction models. For this purpose, we used data of all patients 18 years or older which were hospitalized for more than a day between January 1, 2014, and December 31, 2018, at a single tertiary teaching hospital in Zurich, Switzerland. A total of 48,840 patients met inclusion criteria. 18,873 (38.6%) were excluded due to missing data. Mean age (SD) of the included 29,967 patients was 71.1 (12.2) years and 12,231 (40.8%) were women. Delirium was assessed with the Delirium Observation Scale (DOS) with a total score of 3 or greater indicating that a patient is at risk for delirium. Additional measures included structured data collected for nursing process planning and demographic characteristics. The performance of the machine learning models was assessed using the area under the receiver operating characteristic curve (AUC). The training set consisted of 21,147 patients (mean age 71.1 (12.1) years; 8,630 (40.8%) women|) including 233,024 observations with 16,167 (6.9%) positive DOS screens. The test set comprised 8,820 patients (median age 71.1 (12.4) years; 3,601 (40.8%) women) with 91,026 observations with 5,445 (6.0%) positive DOS screens. Overall, the gradient boosting machine model performed best with an AUC of 0.933 (95% CI, 0.929 - 0.936). In conclusion, machine learning models based only on structured nursing data can reliably predict patients at risk for delirium in an acute care setting. Prediction models, using existing data collection processes, could reduce the resources required for delirium screening procedures in clinical practice.

Delirium in elderly patients: Prospective prevalence across hospital services.

OBJECTIVES: This study aimed to determine the 1-year prevalence of delirium and the impact of hospitalization characteristics on delirium across 34 services. METHODS: In this prospective cohort study of elderly in-patients (>65 years, N = 10,261), delirium was determined with the Delirium Observation Screening Scale (DOS) and the Intensive Care Delirium Screening Checklist (ICDSC) in a single sample over one year. We calculated univariate and multiple logistic regression analyses to understand the power of association between delirium, 34 services, sociodemographic, and admission/discharge factors. RESULTS: The prevalence of delirium across all included services was 32%. The odds of developing delirium was highest for intensive care units (ICU, 83.3%, OR 12.34), high for intermediate care units (IMC, 39.8%, OR 1.42) and medical services (34.2%, OR 1.19), and lower for surgical services (28.7%, OR 0.72). Compared with patients without delirium, patients with delirium were older (76.6 vs. 75 years), hospitalized twice as long (14.3 vs. 7.7 days), more commonly had pre-existent dementia (OR 11.98), and were more likely to die in-hospital (OR 24.20) and be admitted from (OR 2.75-2.97) and discharged to institutions (OR 1.66-3.97). CONCLUSION: This study elaborated on the 1-year prevalence of delirium across 34 services and confirmed previous pooled findings in addition to providing new insights regarding the course of hospitalization in elderly patients.

The predisposing and precipitating risk factors for delirium in neurosurgery: a prospective cohort study of 949 patients.

BACKGROUND: Delirium is the most common neuropsychiatric presentation during hospitalization. In neurosurgery, studies on predisposing and precipitating risk factors for the development of delirium are rare but required for the individual risk estimation. METHODS: Prospective cohort study in a tertiary university center. In total, 949 neurosurgical patients, 307 with and 642 without delirium, were included. Demographic factors, neurosurgery-related, neurological, and medical clusters were tested as predictors of delirium in multiple logistic regression analyses. RESULTS: The incidence of delirium in this cohort of neurosurgical patients was 32.4%. Compared to patients without delirium, those with delirium were significantly older, more cognitively and neurologically impaired, transferred from hospitals and nursing homes, admitted as emergencies, longer hospitalized (16.2 vs. 9.5 days; p < 0.001), in greater need of intensive care management, and more frequently transferred to rehabilitation. Predisposing factors of delirium were stroke (OR 5.45, CI 2.12-14.0, p < 0.001), cardiac insufficiency (OR 4.59, CI 1.09-19.26, p = 0.038), cerebral neoplasm (OR 1.53, CI 0.92-2.54, p = 0.019), and age ≥ 65 years (OR 1.47, CI 1.03-2.09, p = 0.030). Precipitating factors of delirium were acute cerebral injury (OR 3.91, CI 2.24-6.83, p < 0.001), hydrocephalus (OR 3.10, CI 1.98-4.87, p < 0.001), and intracranial hemorrhage (OR 1.90, CI 1.23-2.94, p = 0.004). CONCLUSIONS: Delirium in acute neurosurgical patients was associated with longer hospitalization. Whereas common etiologies of delirium like infections and dementia, did not predict delirium, pre-existing neurovascular and traumatic diseases, as well as surgery-related events seem important risk factors contributing to delirium in neurosurgery.

[Diagnosis, differential diagnosis and therapy of substance use disorders in general hospital (general section)]. / Diagnose, Differentialdiagnose und Behandlung von Abhängigkeitserkrankungen im Allgemeinkrankenhaus (allgemeiner Teil).

Substance use disorders are becoming an increasingly significant problem in general hospitals and hence play a key role in consultation- and liaison psychiatry. Diverse psychotropic effects of various substances mimic psychiatric disorders. An alcohol intoxication can present depressive or manic symptoms, a cannabis delirium can present as a psychosis while stimulants use can suggest the diagnosis of an anxiety disorder. Obtaining dual diagnoses by identifying substance-induced and non-substance-induced psychopathologies is clinically challenging.The aim of this article is to systematically describe the psychopathology, pathophysiology and therapeutic options of substance-use disorders particularly relevant for consultation and liaison psychiatry.