Patient zone monitoring for the early delirium risk factor detection with artificial intelligence
Recruiting
- Conditions
- F05.9Delirium, unspecified
- Registration Number
- DRKS00034280
- Lead Sponsor
- niversitätsmedizin Greifswald
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Recruiting
- Sex
- All
- Target Recruitment
- 100
Inclusion Criteria
Admission to ward C3 of the Department of Neurology
-Capable of consenting independently
-Presence of a consent form
Exclusion Criteria
- Isolation due to multidrug-resistant organisms
- Inability of patients to read and/or speak German
Study & Design
- Study Type
- observational
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Risk score for delirium during hospitalization using an AI-based algorithm based on sensordata (light, noise, movement, air quality, temperature, atmospheric pressure, humidity) in the patient environment
- Secondary Outcome Measures
Name Time Method - Delirium incidence (CAM score)<br>- Duration of delirium (days)<br>- Delirium phenotype: hypo-/hyperactive or mixed (RASS score)<br>- Cognitive status (MoCA)<br>- Clinical treatment data (Demographics and social history (NINDS CDE*), Medical history (NINDS CDE*), Sensory impairment (vision aids, hearing aids), Medication history (NINDS CDE*), Substance abuse (AUDIT, NINDS CDE*), Cognitive function (Montreal Cognitive Assessment, MoCA), Surgeries, Stay in an intensive care unit, Transfusions, Complications, Number and type of accesses (e.g., cannulas, central venous catheters, arterial blood pressure measurement, nasogastric or percutaneous feeding tube, suprapubic or indwelling urinary catheter, possibly further drains), Discharge/transfer destination, Hospital stay duration)<br>*NINDS CDE = National Institutes of Neurological Disorders and Stroke Common Data Elements(https://www.commondataelements.ninds.nih.gov/Stroke.aspx#tab=Data_Standards)