Development and validation of a prediction model for 1-year all-cause rehospitalisation after discharge in patients with heart failure with preserved ejection fraction based on the systemic immune-inflammation index - Summary - MDSpire
Advertisement
Development and validation of a prediction model for 1-year all-cause rehospitalisation after discharge in patients with heart failure with preserved ejection fraction based on the systemic immune-inflammation index
To create and internally assess a model for forecasting the likelihood of at least one all-cause readmission within one year post-discharge in HFpEF patients, focusing on the systemic immune-inflammation index (SII).
Key Findings:
Final model retained LnSII, LnNT-proBNP, LnLp(a), GFR, and hypertension as predictors.
Model showed strong discrimination with AUC of 0.8468 (training) and 0.8302 (validation).
Sensitivity and specificity at optimal threshold were 0.7101 and 0.8993 (training), 0.5333 and 0.8750 (validation).
Calibration was acceptable in both cohorts.
Interpretation:
The model demonstrates strong predictive capability for 1-year all-cause readmission in HFpEF patients, suggesting clinical applicability, but requires external validation.
Limitations:
Single-center study may limit generalizability.
Internal validation only; external validation needed for broader applicability.
Retrospective nature may affect data reliability.
Conclusion:
A predictive model with five variables effectively forecasts 1-year readmission in HFpEF patients, warranting external validation before wider use.
