Interpretable machine learning for identifying ICU readmission risk in subgroups with probabilistic rules

Key Points

• To identify risk factors for ICU readmission using interpretable machine learning approaches.
• Utilized machine learning algorithms to analyze patient data from ICU admissions.
• Developed probabilistic rules to interpret the risk of readmission for different subgroups.
• Examined various metrics to evaluate the performance of the models.
• Identified key attributes that contribute to ICU readmission risk.
• Achieved higher accuracy in predicting readmissions compared to traditional methods.
• Probabilistic rules provided clear, actionable insights for clinicians.