Effectiveness of an Analytics-Based Intervention for Reducing Sleep Interruption in Hospitalized Patients

Abstract

IMPORTANCE Sleep has major consequences for physical and emotional well-being. Hospitalized patients experience frequent iatrogenic sleep interruptions and there is evidence that such interruptions can be safely reduced.OBJECTIVE To determine whether a clinical decision support tool, powered by real-time patient data and a trained prediction algorithm, can help physicians identify clinically stable patients and safely discontinue their overnight vital sign checks. DESIGN, SETTING, AND PARTICIPANTSA randomized clinical trial, with inpatient encounters randomized 1:1 to intervention vs usual care, was conducted from March 11 to November 24, 2019. Participants included physicians serving on the primary team of 1699 patients on the general medical service (not in the intensive care unit) of a tertiary care academic medical center.INTERVENTIONS A clinical decision support notification informed the physician if the patient had a high likelihood of nighttime vital signs within the reference ranges based on a logistic regression model that used real-time patient data as input. The notification provided the physician an opportunity to discontinue measure of nighttime vital signs, dismiss the notification for 1 hour, or dismiss the notification for that day. MAIN OUTCOMES AND MEASURESThe primary outcome was delirium, as determined by bedside nurse assessment of Nursing Delirium Screening Scale scores, a standardized delirium screening tool (delirium diagnosed with score Ն2). Secondary outcomes included mean nighttime vital sign checks. Potential harms included intensive care unit transfers and code blue alarms. All analyses were conducted on the basis of intention-to-treat.RESULTS A total of 1930 inpatient encounters in 1699 patients (intervention encounters: 566 of 966 [59%] men; mean [SD] age, 53 [15] years) were randomized. In the intervention vs control arm, there was a significant decrease in the mean (SD) number of nighttime vital sign checks (0.97 [0.95] vs 1.41 [0.86]; P < .001) with no increase in intensive care unit transfers (49 [5%] vs 47 [5%]; P = .92) or code blue alarms (2 [0.2%] vs 9 [0.9%]; P = .07). The incidence of delirium was not significantly reduced (108 [11%] vs 123 [13%]; P = .32).CONCLUSIONS AND RELEVANCE While this randomized clinical trial found no difference between groups in the primary outcome, delirium incidence, the secondary findings indicate that a real-time prediction algorithm embedded within a clinical decision support tool in the electronic health record can help physicians identify clinically stable patients who can forgo routine vital sign checks, safely giving them greater opportunity to sleep. Other aspects of hospital care that depend on clinical stability, such as level of care or cardiac monitoring, may be amenable to a similar intervention.

Tom Nolan's research reviews—13 January 2022

“…Might there be a digital solution to the sleep deprivation of hospital in-patients? Researchers in California devised a decision support tool driven by a “real-time prediction algorithm” to see if identifying inpatients on general wards who could safely forgo four hourly observations overnight would reduce the incidence of delirium 2. It didn’t, but neither did they see any increase in intensive care admissions or resuscitation calls.…”

Timing of blood draws among hospitalized patients: An evaluation of the electronic health records from a large health care system

“…[6][7][8] Avoidance of routine nonurgent early morning blood draws represents a potential solution to decrease interruptions in patients' sleep. [9][10][11][12] However, little is known about the degree to which blood draw patterns contribute to early morning disruptions and whether there has been recent progress in reducing them.…”

A Good Night’s Sleep in the Hospital

“…As the authors mention, patient-care assistants and nurses may not notice the orders have changed because many staff are accustomed to thinking that regular measure of vital signs is a good practice. 2 Potentially user-friendly electronic health record displays and alert optimization for the workflows of staff could be beneficial. Future work in this area could focus on an interdisciplinary approach including nurses and patient-care assistants.…”

“…In this issue of JAMA Internal Medicine , Najafi et al report on their attempt to remove one of these obstacles to a good night of sleep in the hospital: frequent measure of vital signs. They conducted a randomized clinical trial that examined the effectiveness of a clinical decision support tool in the electronic health record to enable physicians to identify patients for whom the frequency of vital sign measurement can be safely reduced at night.…”

“…This challenge is partially owing to clinical complexity: the number of data points that clinicians need to consider in determining stability can be overwhelming. The algorithms created by Najafi et al predicted normal nighttime vital signs 84% of the time and abnormal vital signs 70% of the time, thereby alleviating cognitive burden to the clinician about vital sign stability and reducing alert fatigue from inappropriate notifications. By including a prompt to change vital sign orders, they also made it easy for physicians to change to a schedule that would not interfere with sleep.…”