Machine Learning Interpretability to Assess the Association Between Time in Tight Range and Mortality in Cardiogenic Shock

Key Points

• To evaluate the association between time in tight range and mortality in cardiogenic shock using machine learning interpretability.
• Utilized machine learning models for risk stratification
• Focused on patients with cardiogenic shock
• Applied SHAP explanations for model transparency
• Identified time in tight range as the primary predictor of mortality
• ML models demonstrated strong performance in clinical application
• Findings support targeted interventions for improved patient outcomes