Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry
This study utilized machine learning algorithms to predict acute brain injury (ABI) in patients on venoarterial extracorporeal membrane oxygenation (VA-ECMO), analyzing data from the Extracorporeal Life Support Organization Registry. It found that longer ECMO duration and higher 24-hour pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO patient groups, highlighting key risk factors for neurological complications in these patients.