Initial arterial pH as a predictor of neurologic outcome after out-of-hospital cardiac arrest: A propensity-adjusted analysis

Kiehl, Erich L.; Amuthan, Ram; Adams, Mark P; Love, Thomas E.; Enfield, Kyle B.; Gimple, Lawrence W.; Cantillon, Daniel J.; Menon, Venu

doi:10.1016/j.resuscitation.2019.03.036

Cited by 14 publications

(14 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initial laboratory data immediately after ROSC have a significant association with neurological outcomes in cardiac arrest survivors. 11 12 13 14 15 16 Establishing prediction models by adding widely available laboratory data might have contributed to the improvement of model performance, despite a smaller sample size than those of previous studies.…”

Section: Discussionmentioning

confidence: 99%

“…In recent studies, initial laboratory results at hospital arrival after OHCA, such as arterial pH, 11 12 serum potassium level, 13 14 and serum creatinine level, 15 16 have been reported to be associated with neurological outcomes after cardiac arrest. Machine learning is a crucial component in the establishment of prediction models that include laboratory test results as features since a variety of laboratory tests are performed and conventional statistical techniques have difficulty handling them.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

et al. 2021

View full text Add to dashboard Cite

Background We performed this study to establish a prediction model for 1-year neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients who achieved return of spontaneous circulation (ROSC) immediately after ROSC using machine learning methods. Methods We performed a retrospective analysis of an OHCA survivor registry. Patients aged ≥ 18 years were included. Study participants who had registered between March 31, 2013 and December 31, 2018 were divided into a develop dataset (80% of total) and an internal validation dataset (20% of total), and those who had registered between January 1, 2019 and December 31, 2019 were assigned to an external validation dataset. Four machine learning methods, including random forest, support vector machine, ElasticNet and extreme gradient boost, were implemented to establish prediction models with the develop dataset, and the ensemble technique was used to build the final prediction model. The prediction performance of the model in the internal validation and the external validation dataset was described with accuracy, area under the receiver-operating characteristic curve, area under the precision-recall curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Futhermore, we established multivariable logistic regression models with the develop set and compared prediction performance with the ensemble models. The primary outcome was an unfavorable 1-year neurological outcome. Results A total of 1,207 patients were included in the study. Among them, 631, 139, and 153 were assigned to the develop, the internal validation and the external validation datasets, respectively. Prediction performance metrics for the ensemble prediction model in the internal validation dataset were as follows: accuracy, 0.9620 (95% confidence interval [CI], 0.9352–0.9889); area under receiver-operator characteristics curve, 0.9800 (95% CI, 0.9612–0.9988); area under precision-recall curve, 0.9950 (95% CI, 0.9860–1.0000); sensitivity, 0.9594 (95% CI, 0.9245–0.9943); specificity, 0.9714 (95% CI, 0.9162–1.0000); PPV, 0.9916 (95% CI, 0.9752–1.0000); NPV, 0.8718 (95% CI, 0.7669–0.9767). Prediction performance metrics for the model in the external validation dataset were as follows: accuracy, 0.8509 (95% CI, 0.7825–0.9192); area under receiver-operator characteristics curve, 0.9301 (95% CI, 0.8845–0.9756); area under precision-recall curve, 0.9476 (95% CI, 0.9087–0.9867); sensitivity, 0.9595 (95% CI, 0.9145–1.0000); specificity, 0.6500 (95% CI, 0.5022–0.7978); PPV, 0.8353 (95% CI, 0.7564–0.9142); NPV, 0.8966 (95% CI, 0.7857–1.0000). All the prediction metrics were higher in the ensemble models, except NPVs in both the internal and the external validation datasets. Conclusion We established an ensemble prediction model for prediction of unfavorable 1-year neurological outcomes in OHCA survivors using four machine learning methods. The prediction perfo...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, the reported predictive accuracies of these single clinical factors from previous studies have been inconsistent, and these parameters cannot sufficiently discriminate between patients with a good prognosis and those with a poor prognosis. Thus, it was considered that a “suitable scaling method” based on a combination of prognostic factors would be useful [ 16 , 19 , 25 , 26 , 27 ].…”

Section: Risk Classification For Estimating the Pcas Severitymentioning

confidence: 99%

Differential Effectiveness of Hypothermic Targeted Temperature Management According to the Severity of Post-Cardiac Arrest Syndrome

Kikutani¹,

Nishikimi²,

Shimatani³

et al. 2021

JCM

View full text Add to dashboard Cite

International guidelines recommend targeted temperature management (TTM) to improve the neurological outcomes in adult patients with post-cardiac arrest syndrome (PCAS). However, it still remains unclear if the lower temperature setting (hypothermic TTM) or higher temperature setting (normothermic TTM) is superior for TTM. According to the most recent large randomized controlled trial (RCT), hypothermic TTM was not found to be associated with superior neurological outcomes than normothermic TTM in PCAS patients. Even though this represents high-quality evidence obtained from a well-designed large RCT, we believe that we still need to continue investigating the potential benefits of hypothermic TTM. In fact, several studies have indicated that the beneficial effect of hypothermic TTM differs according to the severity of PCAS, suggesting that there may be a subgroup of PCAS patients that is especially likely to benefit from hypothermic TTM. Herein, we summarize the results of major RCTs conducted to evaluate the beneficial effects of hypothermic TTM, review the recent literature suggesting the possibility that the therapeutic effect of hypothermic TTM differs according to the severity of PCAS, and discuss the potential of individualized TTM.

show abstract

“…One of the most readily available blood tests in the ED is the venous or arterial blood gas measurement, which affords rapid point‐of‐care assessment of a patient's pH. Studies that have evaluated the ability of initial arterial pH (within 2 hours of return of spontaneous circulation) to predict outcome have found no significant association between a pH above 7.1 and neurologic recovery 52 . Although a pH equal to or below 7 had 4.5 greater odds for a poor neurologic outcome, there were some survivors discharged neurologically intact with initial pH below 7, making pH alone an imperfect prognostic tool.…”

Section: Laboratory Testingmentioning

confidence: 99%

Neurologic prognostication after resuscitation from cardiac arrest

2020

View full text Add to dashboard Cite

Out‐of‐hospital cardiac arrest remains a leading cause of mortality in the United States, and the majority of patients who die after achieving return of spontaneous circulation die from withdrawal of care due to a perceived poor neurologic prognosis. Unfortunately, withdrawal of care often occurs during the first day of admission and research suggests this early withdrawal of care may be premature and result in unnecessary deaths for patients who would have made a full neurologic recovery. In this review, we explore the evidence for neurologic prognostication in the emergency department for patients who achieve return of spontaneous circulation after an out‐of‐hospital cardiac arrest.

show abstract

Initial arterial pH as a predictor of neurologic outcome after out-of-hospital cardiac arrest: A propensity-adjusted analysis

Cited by 14 publications

References 42 publications

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

Differential Effectiveness of Hypothermic Targeted Temperature Management According to the Severity of Post-Cardiac Arrest Syndrome

Neurologic prognostication after resuscitation from cardiac arrest

Contact Info

Product

Resources

About