De-escalating Vital Sign Checks
Trial question
Can a real-time predictive algorithm reduce delirium and help physicians identify patients who can safely forgo their vital signs checks?
Study design
Single center
Open label
RCT
Population
Characteristics of study participants
42.0% female
58.0% male
N = 1930
1930 patients (818 female, 1112 male).
Inclusion criteria: hospitalized adult patients who were not in the ICU.
Key exclusion criteria: admission to the ICU.
Interventions
N=966 clinical decision support notification (informs the physician that the patient is predicted to have normal nighttime vital signs and offers sleep-promoting vitals order).
N=964 usual care (the physician does not receive a clinical decision support notification about vital sign prediction).
Primary outcome
Delirium
11%
13%
13.0 %
9.8 %
6.5 %
3.3 %
0.0 %
Clinical decision support
notification
Usual
care
No significant
difference ↔
No significant difference in delirium (11% vs. 13%; RR 0.85, 95% CI -0.81 to 2.51).
Secondary outcomes
Significant decrease in the number of nighttime vital sign checks (0.97 vs. 1.41; RR 0.69, 95% CI 0.28 to 1.1).
No significant difference in ICU transfers (5% vs. 5%; RR 1, 95% CI -16.93 to 18.93).
Borderline significant decrease in code blue alarms (0.2% vs. 0.9%; RR 0.22, 95% CI -0.02 to 0.46).
Conclusion
In hospitalized adult patients who were not in the ICU, clinical decision support notification was not superior to usual care with respect to delirium.
Reference
Nader Najafi, Andrew Robinson, Mark J Pletcher et al. Effectiveness of an Analytics-Based Intervention for Reducing Sleep Interruption in Hospitalized Patients: A Randomized Clinical Trial. JAMA Intern Med. 2022 Feb 1;182(2):172-177.
Open reference URL