Digital health strategies to support clinician icu population management: a crossover study

Introduction: The quantity of information generated for the intensive care unit (ICU) patient can be 10 times more than in other hospital settings. This information burden can strain cognitive reasoning, hinder medical decision making, and cause medical errors. The aim of this study was to investigate whether a novel Acute care Multi-Patient viewer (AMP), created with an understanding of clinician information and process requirements, could reduce time to clinical decision and action by clinicians caring for populations of acutely ill patients compared to a widely used commercial Electronic Medical Record (EMR). Methods: We conducted a randomized crossover study at a quaternary care academic hospital. We compared ICU clinician performance in structured clinical task completion using two electronic environments – a standard EMR versus AMP. The task scenario included assessment of one entire unit and 4 individual patients using the assigned electronic environment (AMP or EMR). We assessed the difference in time required to complete structured task, the task load of clinicians performing the task measured in the range between 0 and 100 using NASA-task load index (NASA-TLX), and the reliability of task completion by the number of errors of cognition made when using AMP versus EMR. Results: 20 subjects (10 pairs of clinicians) participated in the study. During the study session, each participant completed the task on 2 ICUs (7-10 beds each) and 8 individual patients. The time for assessment of the entire ICU and the total time to task completion were significantly lower using AMP versus standard commercial EMR (the median difference in time was -6.11 minutes (IQR -7.91, -4.30) and -5.38 minutes (IQR -7.56, -3.20) respectively, p< 0.001). The time for assessment of the individual patients was similar using both the EMR and AMP (p=0.078). AMP was associated with a significantly lower clinician task load versus EMR (NASA-TLX lower by 22.6 points (IQR 12.4, 32.7); p< 0.001). The difference in total errors per user using AMP vs EMR was not statistically significant (p=0.078). Conclusions: When compared to the standard EMR, AMP significantly reduced time to clinical task completion and clinician task load. Additional research is needed to assess the clinicians’ performance while using AMP in the “live” ICU setting.