Early 24-Hour Changes in Systemic Immune-Inflammation Index Predict Acute Kidney Injury and Mortality in ICU Patients

Area of Science:

• Critical Care Medicine
• Nephrology
• Immunology

Background:

• Acute kidney injury (AKI) and mortality are significant concerns in critically ill patients.
• Predictive models for these outcomes often require improvement for enhanced accuracy.

Purpose of the Study:

• To investigate if early dynamic changes in the systemic immune-inflammation index (SII) improve the prediction of AKI and 1-year mortality in intensive care unit (ICU) patients.
• To develop and validate a prognostic nomogram incorporating SII metrics for improved risk stratification.

Main Methods:

• Retrospective cohort study of 17,491 ICU admissions from the MIMIC-IV database.
• Calculation of three SII metrics within the first 24 hours: 24-h SII_slope, SII_min, and SII_max.
• Use of LASSO-selected logistic regression for AKI prediction and Cox models for mortality, alongside nomogram development and performance evaluation (AUC, calibration, DCA).

Main Results:

• A steeper 24-h SII_slope was identified as an independent predictor of AKI (AUC 0.739).
• Higher SII_min and SII_max were associated with reduced 1-year survival (log-rank p=0.047 for SII_min quartiles).
• The developed nomogram showed excellent discrimination for 1-year mortality (AUC 0.823) with good calibration and clinical utility.

Conclusions:

• Early dynamic changes in SII, specifically the 24-h slope and first-day extremes, independently predict AKI and long-term mortality in ICU patients.
• A nomogram integrating SII metrics with standard severity scores offers a valuable tool for individualized risk stratification in critical care settings.