Skip to main content

Table 2 “Expert” Candidate Predictors of Hospital-induced Delirium (n = 40)

From: Application of a practice-based approach in variable selection for a prediction model development study of hospital-induced delirium

Administrative

Diagnosis

Laboratory Test

Medication

Nursing Assessment

Surgery

Age*

Length of hospital stay*

Length of intensive care unit stay*

Alcohol use*

Alzheimer’s disease*

Anxiety*

Cerebral edema

Dementia*

Depression*

History of delirium*

Mental disorder*

Neurologic disease*

Post-surgical complications

Psychosis

Respiratory disease

Respiratory failure*

Respiratory infection

Sepsis

Shock

Sleep disorder

Substance use

Trauma*

Urinary tract infection*

Prolonged bleeding (due to overanticoagulation and/or procedure)

Fentanyl

Minerals and electrolytes*

Opioids

Propofol*

Psychotherapeutic agents*

Sedatives*

Cognitive status*

NPO state

Pain*

Psychological status

Risk of falls

Sleep deprivation*

General anesthesia*

Neurosurgery

Surgery*

Trauma surgery

  1. Note. The candidate predictors are organized by operational category based on how they were most accurately and reliably represented in our local EHR system, Epic. EHR = electronic health record; NPO = nil per os (“nothing by mouth”).
  2. * Empirical predictors of hospital-induced delirium (candidate predictors that were included in the final prognostic models of hospital-induced delirium in the model development-and-validation studies based on statistical methods (see Table S1 in the Supplementary Material for the list of studies)).
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us