• Jonathan Elmer, Michael C Kurz, Patrick J Coppler, Alexis Steinberg, Stephanie DeMasi, Maria De-Arteaga, Noah Simon, Vladimir I Zadorozhny, Katharyn L Flickinger, Clifton W Callaway, and University of Pittsburgh Post-Cardiac Arrest Service.
• Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA.
• Crit. Care Med. 2023 Apr 1; 51 (4): 503512503-512.

ObjectivesWithdrawal of life-sustaining therapies for perceived poor neurologic prognosis (WLST-N) is common after resuscitation from cardiac arrest and may bias outcome estimates from models trained using observational data. We compared several approaches to outcome prediction with the goal of identifying strategies to quantify and reduce this bias.DesignRetrospective observational cohort study.SettingTwo academic medical centers ("UPMC" and "University of Alabama Birmingham" [UAB]).PatientsComatose adults resuscitated from cardiac arrest.InterventionNone.Measurements And Main ResultsAs potential predictors, we considered clinical, laboratory, imaging, and quantitative electroencephalography data available early after hospital arrival. We followed patients until death, discharge, or awakening from coma. We used penalized Cox regression with a least absolute shrinkage and selection operator penalty and five-fold cross-validation to predict time to awakening in UPMC patients and then externally validated the model in UAB patients. This model censored patients after WLST-N, considering subsequent potential for awakening to be unknown. Next, we developed a penalized logistic model predicting awakening, which treated failure to awaken after WLST-N as a true observed outcome, and a separate logistic model predicting WLST-N. We scaled and centered individual patients' Cox and logistic predictions for awakening to allow direct comparison and then explored the difference in predictions across probabilities of WLST-N. Overall, 1,254 patients were included, and 29% awakened. Cox models performed well (mean area under the curve was 0.93 in the UPMC test sets and 0.83 in external validation). Logistic predictions of awakening were systematically more pessimistic than Cox-based predictions for patients at higher risk of WLST-N, suggesting potential for self-fulfilling prophecies to arise when failure to awaken after WLST-N is considered as the ground truth outcome.ConclusionsCompared with traditional binary outcome prediction, censoring outcomes after WLST-N may reduce potential for bias and self-fulfilling prophecies.Copyright © 2023 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved.

14 keywords...

hide…