Can an interpretable machine learning model accurately predict the risk of new-onset atrial fibrillation in critically ill patients without cardiac surgery?
An interpretable machine learning model can predict new-onset atrial fibrillation in critically ill patients, potentially aiding clinicians in early prevention and improving outcomes.
We developed a ML model to predict the risk of NOAF in critically ill patients without cardiac surgery and validated its potential as a clinically reliable tool. SHAP improves the interpretability of the model, enables clinicians to better understand the causes of NOAF, helps clinicians to prevent it in advance and improves patient outcomes.
Guan et al. (Tue,) studied this question.