Documenting Rapid Response System afferent limb failure and associated patient outcomes

Trinkle, Rebecca M.; Flabouris, Arthas

doi:10.1016/j.resuscitation.2011.03.019

Cited by 150 publications

(116 citation statements)

References 29 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…An RRS was used for only 30% of patients before unplanned intensive care unit admission and was not used for 22.8% of patients, even if they met the criteria 18, 19. Consequently, most previous studies focused on improving sensitivity 20, 21.…”

Section: Introductionmentioning

confidence: 99%

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

Kwon

Lee²,

Lee³

et al. 2018

JAHA

234

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

234

205

View full text Add to dashboard Cite

show abstract

“…Our findings of delayed or absent MET calls in over 50% are of concern, since studies showed an association between MET consult delays and SAEs [10,[14][15][16][17]25] . Regular monitoring of vital signs is the first and foremost step of the afferent procedure for detecting critically ill patients.…”

Section: Discussionmentioning

confidence: 57%

“…Even in matured RRSs, failure of the afferent limb is a persistent problem [13] which may result in cardiac arrests [14] , hospital mortality [10,15,16] or increased unplanned ICU admissions [10,17] . Until now, studies on the effects of an RRS remain equivocal [7,[18][19][20] .…”

Section: Introductionmentioning

confidence: 99%

Effect of implementation of a rapid response system on protocol adherence in a surgical ward

Simmes

Schoonhoven²,

Mintjes

et al. 2013

JHA

View full text Add to dashboard Cite

Objective: To describe the implementation of a rapid response system and adherence to its afferent limb in order to identify key elements for improvement. Implementation:We developed a multifaceted implementation strategy to introduce the Rapid Response System (RRS) on a 60-bed surgical ward of a university hospital. The strategy included the use of clear objectives, key leaders, an early warning score (EWS) observation protocol and a two-tiered medical emergency team (MET) warning protocol, a 1-day training program including a before-after knowledge test, mandatory for nurses and optional for ward physicians, reminders and feedback. Study design and methods:We retrospectively analyzed a sample of 10,653 patient days and 101 medical records of patients with a serious adverse event (SAE). Outcome measures were EWS recording rates, the nurse to ward physician and the ward physician to the MET calling rates following abnormal EWS recordings, and the indicators triggering these calls.Results: EWS recordings were present in 90% of the day shifts, 88% of the evening shifts and 80% of the night shifts. EWSs were recorded at least once in 92/101 medical records in the three days before an SAE; in 91/101 records EWSs were abnormal at least once. In case of an abnormal score, the nurse called the ward physician once or more in 87% (79/91). After being called by the nurse, the ward physician called the MET once or more in 75% (59/79). However, in 18% (15/79) there was a delay of one or two days before the ward physician/MET was called. Overall, medical emergency team calls were absent or delayed in over 50%. Conclusions:After RRS implementation, recording of the EWS was high. Adequate warning in case of abnormal scores was suboptimal in nurses as well as ward physicians. Future implementation strategies should therefore be aimed at the interdisciplinary team.

show abstract

mentioning

confidence: 99%

“…A recent study demonstrated that afferent limb failure was present on 23% of cardiac arrest patients needing unplanned ICU admissions or Medical emergency team calls [13]. Such afferent limb failures have been shown to increase the mortality of patients [13]. Other studies have noted that respiratory rate is one of the physical examination finding noted least by the primary care teams, so much so it has been termed "the neglected sign" by some investigators [14].…”

mentioning

confidence: 99%

Early Warning Scores-Are We Doing it Right?

Samarakoon¹

2015

J Nurs Care

View full text Add to dashboard Cite

Documenting Rapid Response System afferent limb failure and associated patient outcomes

Cited by 150 publications

References 29 publications

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

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

Effect of implementation of a rapid response system on protocol adherence in a surgical ward

Early Warning Scores-Are We Doing it Right?

Contact Info

Product

Resources

About