Rapid-Response Teams

Jones, Daryl; DeVita, Michael A.; Bellomo, Rinaldo

doi:10.1056/nejmra0910926

Cited by 661 publications

(535 citation statements)

References 48 publications

(75 reference statements)

Supporting

Mentioning

515

Contrasting

Unclassified

Order By: Relevance

“…However, 209 000 in‐hospital cardiac arrests occur in the United States each year, and the survival discharge rate for patients with cardiac arrest is <20% worldwide 10, 11. Rapid response systems (RRSs) have been introduced in many hospitals to detect cardiac arrest using the track‐and‐trigger system (TTS) 12, 13…”

Section: Introductionmentioning

confidence: 99%

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Kwon

Lee²,

Lee³

et al. 2018

JAHA

221

205

View full text Add to dashboard Cite

BackgroundIn‐hospital cardiac arrest is a major burden to public health, which affects patient safety. Although traditional track‐and‐trigger systems are used to predict cardiac arrest early, they have limitations, with low sensitivity and high false‐alarm rates. We propose a deep learning–based early warning system that shows higher performance than the existing track‐and‐trigger systems.Methods and ResultsThis retrospective cohort study reviewed patients who were admitted to 2 hospitals from June 2010 to July 2017. A total of 52 131 patients were included. Specifically, a recurrent neural network was trained using data from June 2010 to January 2017. The result was tested using the data from February to July 2017. The primary outcome was cardiac arrest, and the secondary outcome was death without attempted resuscitation. As comparative measures, we used the area under the receiver operating characteristic curve (AUROC), the area under the precision–recall curve (AUPRC), and the net reclassification index. Furthermore, we evaluated sensitivity while varying the number of alarms. The deep learning–based early warning system (AUROC: 0.850; AUPRC: 0.044) significantly outperformed a modified early warning score (AUROC: 0.603; AUPRC: 0.003), a random forest algorithm (AUROC: 0.780; AUPRC: 0.014), and logistic regression (AUROC: 0.613; AUPRC: 0.007). Furthermore, the deep learning–based early warning system reduced the number of alarms by 82.2%, 13.5%, and 42.1% compared with the modified early warning system, random forest, and logistic regression, respectively, at the same sensitivity.ConclusionsAn algorithm based on deep learning had high sensitivity and a low false‐alarm rate for detection of patients with cardiac arrest in the multicenter study.

show abstract

Section: Introductionmentioning

confidence: 99%

An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Kwon

Lee²,

Lee³

et al. 2018

JAHA

221

205

View full text Add to dashboard Cite

show abstract

“…3 Thus, METs are well positioned to discuss preferences for cardiopulmonary resuscitation in a population at high risk for cardiac arrest. 4 MET activations involve a change in code status in approximately 3% to 10% of cases. [5][6][7][8] However, previous studies primarily involved hospitals in Australia, making the results difficult to generalize to other countries.…”

Section: Resultsmentioning

confidence: 99%

Resource utilization and end‐of‐life care in a US hospital following medical emergency team‐implemented do not resuscitate orders

Dargin

Mackey

et al. 2014

Journal of Hospital Medicine

View full text Add to dashboard Cite

BACKGROUND: Medical emergency teams frequently implement do not resuscitate orders, but little is known about end-of-life care in this population. OBJECTIVE:To examine resource utilization and end-of-life care following medical emergency team-implemented do not resuscitate orders. DESIGN: Retrospective review.SETTING: Single, tertiary care center. PATIENTS:Consecutive adult inpatients requiring a medical emergency team activation over 1 year. MEASUREMENTS:Changes to code status, time spent on medical emergency team activations, frequency of palliative care consultation, discharges with hospice care.

show abstract

“…Irrespective of their nomenclature, the aim of RRTs is to improve the safety of deteriorating ward patients [1]. The RRT approach is based on (a) identification of patients at risk; (b) early notification of a team; (c) rapid intervention by the team and (d) audit of the system's performance [2].…”

mentioning

confidence: 99%

“…However, a major multicentre cluster randomised controlled trial called MERIT failed to demonstrate a benefit. Moreover, meta-analyses have been variable in their conclusions; several authors have questioned whether tangible benefits really exist and suggested that further higher level research and trials are required [2]. In this setting, a major practice question for many institutions in 2016, therefore, is whether the evidence is now strong enough to be sure that their introduction is clearly justified or, instead, so weak or poor that their introduction is likely a pointless and expensive misallocation of resources.…”

mentioning

confidence: 99%

“…They include the need for a long run-in period; the benefit of team training; the advantage of ensuring critical care medical input; the need to deliver a sufficient dose of intervention (number of calls/1000 patients); the need to optimise the performance of the afferent limb of the system (the component responsible for calling the team); the need for sufficient administrative and political institutional support, and, finally, the full commitment of the critical care team and department to ensure performance, monitoring and continued improvement of the RRT. Subsequent studies, which analysed the data from different perspectives, have argued that there was in fact an effect on cardiac arrests and mortality [2] (Table 1). Unfortunately, however, such post hoc analyses carry a significant risk of type I error, leaving clinicians still uncertain about the presence of a true beneficial effect.…”

mentioning

confidence: 99%

See 1 more Smart Citation