Part 4: Systems of Care and Continuous Quality Improvement

Kronick, Steven L.; Kurz, Michael C.; Lin, Steve; Edelson, Dana P.; Berg, Robert A.; Billi, John E.; Cabañas, José G.; Cone, David C.; Diercks, Deborah B.; Foster, James Jim; Meeks, Reylon A.; Travers, Andrew H.; Welsford, Michelle

doi:10.1161/cir.0000000000000258

Cited by 235 publications

(94 citation statements)

References 144 publications

(112 reference statements)

Supporting

Mentioning

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

235

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

235

205

View full text Add to dashboard Cite

show abstract

“…However, the proportion of patients who receive bystander CPR, following an out‐of‐hospital cardiac arrest (OHCA), is still relatively low in most countries 3. Fortunately, bystander CPR rates in some countries have recently increased to ≈50% 4, 5, 6, 7, 8, 9.…”

Section: Introductionmentioning

confidence: 99%

Relationship Between Emergency Medical Services Response Time and Bystander Intervention in Patients With Out‐of‐Hospital Cardiac Arrest

Goto

Funada

Goto

2018

JAHA

View full text Add to dashboard Cite

BackgroundThe response time of emergency medical services (EMS) is an important determinant of survival after out‐of‐hospital cardiac arrest. We sought to identify upper limits of EMS response times and bystander interventions associated with neurologically intact survival.Methods and ResultsWe analyzed the records of 553 426 patients with out‐of‐hospital cardiac arrest in a Japanese registry between 2010 and 2014. The primary study end point was 1‐month neurologically intact survival (Cerebral Performance Category scale 1 or 2). Increased EMS response time was associated with significantly decreased adjusted odds of 1‐month neurologically intact survival (adjusted odds ratio [aOR] for each 1‐minute increase, 0.89; 95% confidence interval [CI], 0.89–0.90), although this relationship was modified by bystander interventions. The bystander interventions and the ranges of EMS response times that were associated with increased adjusted 1‐month neurologically intact survival were as follows: bystander defibrillation, from ≤2 minutes (aOR, 3.10 [95% CI, 1.25–7.31]) to 13 minutes (aOR, 5.55 [95% CI, 2.66–11.2]); bystander conventional cardiopulmonary resuscitation, from 3 minutes (aOR 1.48 [95% CI, 1.02–2.12]) to 11 minutes (aOR 2.41 [95% CI, 1.61–3.56]); and bystander chest‐compression‐only cardiopulmonary resuscitation, from ≤2 minutes (aOR 1.57 [95% CI, 1.01–2.25]) to 11 minutes (aOR 1.92 [95% CI, 1.45–2.56]). However, the increase in neurologically intact survival of those receiving bystander interventions became statistically insignificant compared with no bystander interventions when the EMS response time was outside these ranges.ConclusionsThe upper limits of the EMS response times associated with improved 1‐month neurologically intact survival were 13 minutes when bystanders provided defibrillation (typically with cardiopulmonary resuscitation) and 11 minutes when bystanders provided cardiopulmonary resuscitation without defibrillation.

show abstract

“…Using a modified Delphi technique, the top 10 list of knowledge gaps included themes related to out‐of‐hospital and in‐hospital cardiac arrest management 25. At the onset of a cardiac arrest event, the expert panel noted the importance of leveraging technology to improve rapid identification and response along with enhancing CPR provision by improving bystander and dispatcher response (telecommunicator CPR).…”

Section: Discussionmentioning

confidence: 99%

Delphi Analysis of Science Gaps in the 2015 American Heart Association Cardiac Arrest Guidelines

Panchal

Cash

Crowe

et al. 2018

JAHA

View full text Add to dashboard Cite

BackgroundCurrent cardiac arrest guidelines have limited high‐quality scientific evidence to support recommendations for care. The quality of scientific evidence on which guidelines are based may correlate with improved patient outcomes and meaningful survival. We sought to develop a prioritized list of knowledge gaps in resuscitation to assist researchers, policy makers, and funding agencies in their decision‐making process.Methods and ResultsA 4‐stage modified Delphi method was used with a panel of cardiac arrest experts. Experts addressed the prompt: “What are the top 3 gaps in knowledge involving cardiac arrest care that should be research priorities for National Institutes of Health/American Heart Association funding to have the greatest impact on public health?” Knowledge gaps were identified in the initial round, rated in a second round, and rank ordered in the third round, and they underwent final review and consensus (final round). The outcome was 10 knowledge gaps, with prioritization of the top 3 gaps. A total of 61 gaps, with 19 distinct themes, were identified by participants. The 10 knowledge gaps most likely to affect public health identified by the expert panel included, in order, the following: telecommunicator cardiopulmonary resuscitation, hemodynamic monitoring for goal‐directed resuscitation, reasons why bystanders fail to respond, optimization of postarrest care, out‐of‐hospital cardiac arrest identification and response, individualizing resuscitation strategies, predicting patients at risk, tools for neuroprognostication, optimal airway management, and optimizing educational strategies.ConclusionsTen priorities for cardiac arrest research were identified, but consensus was not reached on the prioritized top 3. Future research should address these gaps to potentially improve resuscitation guideline evidence quality.

show abstract

Part 4: Systems of Care and Continuous Quality Improvement

Cited by 235 publications

References 144 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

Relationship Between Emergency Medical Services Response Time and Bystander Intervention in Patients With Out‐of‐Hospital Cardiac Arrest

Delphi Analysis of Science Gaps in the 2015 American Heart Association Cardiac Arrest Guidelines

Contact Info

Product

Resources

About