Frequency of medical emergency team activation prior to pediatric cardiopulmonary resuscitation

The Deterioration Risk Index: Developing and Piloting a Machine Learning Algorithm to Reduce Pediatric Inpatient Deterioration

OBJECTIVES

Develop and deploy a disease cohort-based machine learning algorithm for timely identification of hospitalized pediatric patients at risk for clinical deterioration that outperforms our existing situational awareness program.

DESIGN

Retrospective cohort study.

SETTING

Nationwide Children's Hospital, a freestanding, quaternary-care, academic children's hospital in Columbus, OH.

PATIENTS

All patients admitted to inpatient units participating in the preexisting situational awareness program from October 20, 2015, to December 31, 2019, excluding patients over 18 years old at admission and those with a neonatal ICU stay during their hospitalization.

INTERVENTIONS

We developed separate algorithms for cardiac, malignancy, and general cohorts via lasso-regularized logistic regression. Candidate model predictors included vital signs, supplemental oxygen, nursing assessments, early warning scores, diagnoses, lab results, and situational awareness criteria. Model performance was characterized in clinical terms and compared with our previous situational awareness program based on a novel retrospective validation approach. Simulations with frontline staff, prior to clinical implementation, informed user experience and refined interdisciplinary workflows. Model implementation was piloted on cardiology and hospital medicine units in early 2021.

MEASUREMENTS AND MAIN RESULTS

The Deterioration Risk Index (DRI) was 2.4 times as sensitive as our existing situational awareness program (sensitivities of 53% and 22%, respectively; p < 0.001) and required 2.3 times fewer alarms per detected event (121 DRI alarms per detected event vs 276 for existing program). Notable improvements were a four-fold sensitivity gain for the cardiac diagnostic cohort (73% vs 18%; p < 0.001) and a three-fold gain (81% vs 27%; p < 0.001) for the malignancy diagnostic cohort. Postimplementation pilot results over 18 months revealed a 77% reduction in deterioration events (three events observed vs 13.1 expected, p = 0.001).

CONCLUSIONS

The etiology of pediatric inpatient deterioration requires acknowledgement of the unique pathophysiology among cardiology and oncology patients. Selection and weighting of diverse candidate risk factors via machine learning can produce a more sensitive early warning system for clinical deterioration. Leveraging preexisting situational awareness platforms and accounting for operational impacts of model implementation are key aspects to successful bedside translation.

Rapid Response Team Activation Triggers in Adults and Children: An Integrative Review

PURPOSE

This integrative review aims to identify the triggers for rapid response team (RRT) activation and their outcomes in pediatric patients and to compare them with those of adult patients. In addition, this integrative review synthesizes the outcomes of cardiopulmonary resuscitation (CPR), intensive care unit (ICU) admission, length of hospital stay, and mortality following RRT activation.

METHOD

An integrative review using the Whittemore and Knafl methodology was undertaken with a search of three large databases (PubMed, Ovid MEDLINE, and CINAHL) and found 25 relevant studies published in the years 2017 through 2022.

RESULTS

Tachypnea, decreased oxygen saturation, tachycardia, changes in blood pressure, and level of consciousness were the most common triggers in both populations. However, specific activation triggers differed between children and adults.

CONCLUSIONS

The most common triggers for RRT are detectable through vital signs monitoring; therefore, vigilant tracking of patients' vital signs is critical and can provide early clues to clinical deterioration.

Emergency Medical Response for Non-Hospitalized Person Events in a Children's Hospital

OBJECTIVES

Hospital-based code blue (CB) teams are designed for hospitalized patients (HP) with unanticipated medical emergencies outside of an ICU. At our freestanding pediatric institution, the same team responds to CB calls involving nonhospitalized persons (NHP) throughout the hospital campus. We hypothesized there are significant differences between the characteristics of NHP and HP requiring emergency medical response, and most responses for NHP do not require advanced critical care.

METHODS

We analyzed a retrospective cohort of CB responses at our large, urban, academic children's medical center from January to December 2017. We evaluated the demographic and clinical characteristics of these HP compared with NHP events.

RESULTS

There were 168 CB activations during the study, of which 135 (80.4%) were for NHP. Ninety-one (67.4%) of the NHP responses involved adults (age >18 years) compared with 6 (18.2%) of the HP. Triggers for CB team activation for NHP were most frequently syncope (42.2%), seizure (10.3%), or fall (9.6%) compared with seizure (30.3%), hypoxia (27.3%), or anaphylaxis (12.1%) for HP. Critical interventions such as bag-mask ventilation and cardiopulmonary resuscitation were infrequently performed for either cohort.

CONCLUSIONS

CB activations in our pediatric institution more often involve NHP than HP. NHP responses are more likely to involve adults and infrequently require advanced interventions. Use of a pediatric CB team for NHP events may be an unnecessary use of pediatric critical care resources. Future studies are warranted to evaluate the most effective team composition, training, and response system for NHP in a freestanding children's hospital.

Implementation of a paediatric early warning system as a complex health technology intervention

The national implementation groups of early warning systems in the UK and Ireland have identified a need to understand implementation, adoption and maintenance of these complex interventions. The literature on how to implement, scale, spread and sustain these systems is sparse. We describe a successful adoption and maintenance over 10 years of a paediatric early warning system as a sociotechnical intervention using the Nonadoption, Abandonment, Challenges to the Scale-Up, Spread, and Sustainability Framework for Health and Care Technologies. The requirement for iterative processes within environment, culture, policy, human action and the wider system context may explain the possible reasons for improved outcomes in small-scale implementation and meta-analyses that are not reported in multicentre randomised control trials of early warning systems.

Early Experience with a Novel Strategy for Assessment of Sepsis Risk: The Shock Huddle

Introduction

Severe sepsis/septic shock (SS), a leading cause of death in children, is a complex clinical syndrome that can be challenging to diagnose. To assist with the early and accurate diagnosis of this illness, we instituted an electronic scoring tool and developed a novel strategy for the assessment of currently hospitalized children at risk for SS.

Methods

The Shock Tool was created to alert providers to children at risk for SS. Above a threshold score of 45, patients were evaluated by a team from the pediatric intensive care unit (PICU), led by the Shock Nurse (RN), a specially trained PICU nurse, to assess their need for further therapies. Data related to this evaluation, termed a Shock Huddle, were collected and reviewed with the intensivist fellow on service.

Results

Over 1 year, 9,241 hospitalized patients were screened using the Shock Score. There were 206 Shock Huddles on 109 unique patients. Nearly 40% of Shock Huddles included a diagnostic or therapeutic intervention at the time of patient assessment, with the most frequent intervention being a fluid bolus. Shock Huddles resulted in a patient transfer to the PICU 10% of the time.

Conclusion

Implementation of an electronic medical record-based sepsis recognition tool paired with a novel strategy for rapid assessment of at-risk patients by a Shock RN is feasible and offers an alternative strategy to a traditional medical emergency team for the delivery of sepsis-related care. Further study is needed to describe the impact of this process on patient outcomes.

No more pediatric code blues on the floor: evolution of pediatric rapid response teams and situational awareness plans

Reducing or eliminating code blues that occur on the inpatient, noncritical care units of children's hospitals is a challenging yet achievable goal. The mechanism to accomplish this involves several levels of effort. The implementation of effective pediatric rapid response teams is a well identified part of the process. Rapid response teams can allow for appropriate clinical interventions for deteriorating patients and may ultimately result in a reduction in hospital-wide mortality as well as efficient transfer to the pediatric intensive care unit (PICU) when necessary. The timely deployment of rapid response teams is dependent upon the appropriate recognition of patients at risk for deterioration. This recognition can be optimized by relying on assessments as simple as utilization of parental intuition to those as complex as big data models which utilize multiple predictor variables extracted from the electronic medical record. Ultimately, the goal to proactively identify patients at risk of deterioration may allow for prevention of clinical decline via appropriate and timely interventions, and if unsuccessful at that level, may allow for improved outcomes via optimized resuscitation care in the PICU.