No abstract

Figure 1. We propose a simple yet effective method for image obfuscation by blurring in latent space (i.e., DeepBlur). Comparing to existing methods (e.g., Gaussian blur, pixelation, masking, and adversarial noise), our approach preserves high perceptual quality while preventing unauthorized face recognition from both automatic systems and human adversaries.

BackgroundHigh incidence of delirium in hospitalized patients has been reported in the United States and is significantly associated with increased morbidity and mortality. The lack of knowledge and confidence in performing delirium assessment (KCDA) has led to significant underrecognition of delirium by nurses regardless of evidence-based education intervention.ObjectiveThe purpose of this study was to determine the effectiveness of a multimodal educational program (MEP) to enhance nurses' KCDA.MethodsA MEP including an online didactic with a video-simulation and 1:1 bedside coaching with delirium screening (DS) was conducted in the surgical intermediate-care unit of an academic medical center. A quasi-experimental pre- and post-test design was used.ResultsOf 23 nurses, the majority were <41 years old (73.9%) and had at least a bachelor of science in nursing degree (78.3%) with <6 years of experience (60.9%). The overall KCDA scores and the performance of DS improved significantly after the MEP (p < .001). A positive correlation was noted between the changes of the KCDA scores (p = .009).ConclusionsThe MEP demonstrated improvement in nurses' KCDA. The MEP should focus on an individualized learning approach with a targeted patient population, using current delirium screening tools.Implications for NursingEducational programs are recommended in either an orientation or continuing education program on nursing units. This is also recommended for use in other academic centers that encompass similar clinical settings and could possibly be considered for use in other disease processes.

No abstract

No abstract