Development and Validation of Scores to Predict Prolonged Mechanical Ventilation after Cardiac Surgery

Abstract

ObjectivesTo optimize the early prediction of prolonged post-operative mechanical ventilation following cardiac surgery (MV) (>24hours post-operatively). DesignRetrospective analysis. SettingAustralian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) database. ParticipantsAll patients included in the ANZSCTS database between January 2015 and December 2018. InterventionsObservational study Measurements and Main ResultsA previously developed model was modified to allow retrospective risk calculation and model assessment (Modified Hessels score). The database was split into development and validation sets. A new risk model was developed using forward and backward stepwise elimination (ANZ-PreVent score). We assessed 48,382 patients, of which 5004 (10.3%) were mechanically ventilated for >24 hours post-operatively. In this database the Modified Hessels score demonstrated good performance, with a c-index of 0.78 (95% CI 0.77 – 0.78) and Brier's score of 0.08. The newly developed ANZ-PreVent score demonstrated better performance (validation cohort, n=12,229), with a c-index of 0.84 (95% CI 0.83 – 0.85) (p<0.0001) and Brier's score of 0.07. Both scores performed better than severity of illness scores commonly used to predict outcomes in intensive care. ConclusionsWe validated a modified version of an existing prediction score and developed the ANZ-PreVent score, with improved performance for the identification of patients at risk of ventilation for >24hours. The improved score can be utilised to identify high risk patients for targeted interventions in future randomised controlled trials.