• Lara Hessels, Tim G Coulson, Siven Seevanayagam, Paul Young, David Pilcher, Nada Marhoon, and Rinaldo Bellomo.
• Data Analytics, Research and Evaluation (DARE) Centre, Austin Hospital, University of Melbourne, Melbourne, Australia; Department of Intensive Care, Austin Hospital, Melbourne, Australia; Department of Critical Care, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
• J. Cardiothorac. Vasc. Anesth. 2019 Oct 1; 33 (10): 2709-2716.

ObjectiveTo develop and validate a score for the early identification of cardiac surgery patients at high risk of prolonged mechanical ventilation (MV) who may be suitable targets for interventional trials.DesignRetrospective analysis.SettingTertiary intensive care unit.ParticipantsCardiac surgery patients.InterventionsObservational study.Measurements And Main ResultsThe study comprised 1,994 patients. Median age was 67 years, and 1,457 patients (74%) were male. Median duration of MV was 9.4 hours. A total of 229 (11%), 182 (9%), and 127 (6%) patients received MV for ≥24, ≥36, and ≥48 hours, respectively. In-hospital mortality was 13%, 15%, and 17%, respectively. For the study model, all preoperative, intraoperative, and early (first 4 hours) postoperative variables were considered. A multivariable logistic regression model was developed, and a predictive scoring system was derived. Using MV ≥24 hours as the primary outcome, the model performance in the development set was good with a c-index of 0.876 (95% confidence interval 0.846-0.905) and a Brier's score of 0.062. In the validation set, the c-index was 0.907 (0.867-0.948), Brier's score was 0.059, and the model remained well calibrated.ConclusionsThe authors developed a simple score to predict prolonged MV after cardiac surgery. This score, if externally validated, is potentially suitable for identifying a high-risk target population for future randomized controlled trials of postoperative care after cardiac surgery.Copyright © 2019 Elsevier Inc. All rights reserved.

37 keywords...

hide…