Development and internal validation of an interpretable machine learning model to predict coagulopathy following extracorporeal membrane oxygenation: a retrospective multicenter study

Key Points

• Coagulopathy prediction accuracy reaches 85%, enhancing clinician decision-making.
• Key features for prediction include patient age and platelet count, essential for reliable outcomes.
• Retrospective multicenter analysis utilizes extensive data, ensuring comprehensive evaluation of predictors.
• Machine learning model may enhance patient outcomes in ECMO management and improve clinical workflows.