Background and Objectives To determine thresholds of serum neuron-specific enolase (NSE) for prediction of poor outcome after cardiac arrest with >95% specificity using a unique method of multiple thresholds meta-analysis. Methods Data from a systematic review by the European Resuscitation Council (ERC 2014) were updated with literature searches from PubMed, Cochrane, and Scopus until August 2020. Search terms included the MeSH terms “heart arrest” and “biomarkers” and the text words “cardiac arrest,” “neuron specific enolase,” “coma” and “prognosis.” Cohort studies with comatose cardiac arrest survivors aged >16 years undergoing targeted temperature management (TTM) and NSE levels within 96 hours of resuscitation were included. Poor outcome was defined as cerebral performance category 3–5 at hospital discharge or later. Studies without extractable contingency tables were excluded. A multiple thresholds meta-analysis model was used to generate summary receiver operating characteristic curves for various time points. NSE thresholds (and 95% prediction intervals) for >95% specificity were calculated. Evidence appraisal was performed using a method adapted from the American Academy of Neurology grading criteria. Results Data from 11 studies (n = 1,982) at 0–24 hours, 21 studies (n = 2,815) at 24–48 hours, and 13 studies (n = 2,557) at 48–72 hours was analyzed. Areas under the curve for prediction of poor outcomes were significantly larger at 24–48 hours and 48–72 hours compared to 0–24 hours (0.82 and 0.83 vs 0.64). Quality of evidence was very low for most studies because of the risk of incorporation bias—knowledge of NSE levels potentially influenced life support withdrawal decisions. To minimize falsely pessimistic predictions, NSE thresholds at the upper 95% limit of prediction intervals are reported. For prediction of poor outcome with specificity >95%, upper limits of the prediction interval for NSE were 70.4 ng/mL at 24–48 hours and 58.6 ng/mL at 48–72 hours. Sensitivity analyses excluding studies with inconsistent TTM use or different outcome criteria did not substantially alter the results. Conclusions NSE thresholds for highly specific prediction of poor outcome are much higher than generally used. Future studies must minimize bias by masking treatment teams to the results of potential predictors and by prespecifying criteria for withdrawal of life support.
ASJC Scopus subject areas
- Clinical Neurology