Project Members: Aileen Naef, Marie-Madlen Jeitziner, René M Müri, Stephan M. Jakob, Tobias Nef
Project Start: 15.09.2019
Critically ill patients who spend time in the intensive care unit (ICU) have been found to frequently develop delirium, with the prevalence in the ICU estimated to be between 35–80% . Delirium is defined as a disturbance in attention, awareness and cognition with reduced ability to direct, focus, sustain and shift attention, and reduced orientation to the environment. Previous studies looking at delirium in the hospital setting have found that the duration of delirium is associated with longer hospital stays, worse long-term cognitive impairment, and increased costs for society.
In prevention and treatment, pharmacological and non-pharmacological approaches are used. Although pharmacologic prevention and treatment of delirium remains controversial, it is still used in the clinical setting. Current evidence does not support the use of non-pharmacological interventions in reducing the incidence of delirium in critically ill patients . However, in clinical practice single- or multicomponent interventions such as reorientation, e.g. early mobilization, communication tools, sleep improvement, and family involvement are often used.
In a previous study, Gerber et al. provided evidence that Virtual Reality (VR) stimulation (i.e. relaxing nature videos) as a new non-pharmacological approach comforts critically ill patients during their stay in the ICU. Building on the work of Gerber et al., we have decided to investigate how showing such videos may effect delirium in the ICU.
Therefore, main goal of this project is to investigate the effect of VR stimulation on delirium while in the ICU, specifically the incidence and duration of delirium. Furthermore, we are also interested in using machine learning to determine if physiological or behavioral parameters can be used to predict delirium onset.
Keywords: Virtual reality, Audio-visual stimulation, Critical illness, Intensive care unit, delirium, machine-learning, motion analysis